Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. It usefully adds the return format (transparent PNG) and a cost signal (2 credits), which is real behavioral information beyond the schema. However, it omits failure behavior, max input size/resolution constraints, and whether credits are charged on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with zero filler; the core action is front-loaded and the output format and cost follow immediately. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with fully documented schema and no output schema, the description covers action, return type, and cost, which is close to sufficient. It stops short of input constraints or failure modes, but nothing critical to making the call is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters (image_url, size with its enum and default) are already documented in structured form. The description adds nothing parameter-specific, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Remove background from any image') and names the output artifact ('transparent PNG'), so an agent immediately knows what the tool produces. It does not explicitly distinguish itself from adjacent siblings such as file-convert or images, but the operation is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says the tool works on 'any image' but gives no when-to-use context, no prerequisites (e.g. image accessibility, format limits), and no alternatives among siblings like file-convert or images. Usage has to be inferred entirely from the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden; it does add real behavioral context by disclosing the sandbox isolation, the pre-configured environment model, and a per-call credit cost. However, it omits whether state/files persist between calls, network access rules, permission requirements, and what the call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, front-loaded sentences with zero filler: the capability first, then the cost. Nothing redundant and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a code-execution tool with no annotations and no output schema, the description leaves major gaps: it does not describe the return shape (stdout/stderr/exit code), persistence of files across calls, or resource limits beyond the schema's timeout. An agent cannot predict the result of invoking it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented in the schema, establishing the baseline of 3. The phrase 'pre-configured environments' loosely echoes the template parameter but adds no syntax or selection guidance beyond the enum values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Execute code') plus the execution context ('secure sandbox with pre-configured environments'). No sibling tool overlaps with code execution, so no differentiation is needed or missing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to choose this tool versus alternatives, nor any prerequisites or exclusions. The only usage-relevant detail is the cost line ('2 credits'), which hints at budget sensitivity but does not tell an agent when invocation is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It does disclose a concrete, non-obvious trait — the 3-credit cost — which is real value since billing affects whether an agent should call it. However, it says nothing about the return shape, whether the operation is read-only or mutating, error behavior for unknown domains, or any auth requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, no filler, and the core purpose is front-loaded ahead of the cost note. Nothing in the text is redundant or wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema and no annotations, the description is minimally viable but leaves real gaps: what the enrichment actually returns (fields, firmographics, confidence) and whether the cost is incurred on failure or repeated calls. An agent can call it, but cannot predict the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and both parameters ('domain' and 'company_name') are documented in the schema itself, so the baseline is 3. The description adds no meaning beyond the schema — it does not clarify the domain format (bare host vs. full URL) or how the optional name hint influences enrichment.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (enrich), resource (company data), and keying input (by domain), so an agent knows exactly what the tool produces. It does not, however, distinguish itself from adjacent siblings like domains, site-intel, or profiles, which could also plausibly take a domain and return company context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no statement of prerequisites, and no reference to any alternative sibling tool. The agent must infer from the description alone that this is the correct tool for domain-based company enrichment versus, say, domains or site-intel.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the credit cost (3 credits), a genuine behavioral trait, and 'extract' implies a read-only operation. But it omits return format, error behavior, rate limits, and auth requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action followed by the cost. Every sentence earns its place and there is no filler. It is tersely efficient, arguably at the edge of being under-specified for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should explain the return shape and when each input mode (url vs. pre-scraped content vs. schema-driven extraction) applies. It does neither, and also fails to differentiate this tool from scrape or research, leaving significant gaps for a 4-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters, making 3 the baseline. The description adds only marginal value by referencing 'URLs or content', mapping loosely to the url and content params, without clarifying the interplay between url, content, extraction_prompt, and schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a clear verb+resource: 'Extract structured data from URLs or content.' This rescues the vague tool name 'documents'. However, it does not differentiate from siblings like scrape, site-intel, or research, which an agent must distinguish by other means.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance. The phrasing implies it is for structured extraction, and the cost note hints at a tradeoff, but no alternative tool is named (scrape vs. research vs. this) so selection among siblings is left entirely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it does add genuinely useful information: exact credit costs per mode. However, it says nothing about read vs write semantics, whether any mode mutates state, rate limits, or failure behavior for the availability checks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, purpose front-loaded before the cost table, and no filler. The cost enumeration is dense but every item maps to a real billable mode, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, multi-mode tool with a nested search_options object and no annotations or output schema, the description covers purpose and billing but omits mode-specific workflows, ordering between modes (e.g. suggest then check-availability), and return expectations. The very complete schema compensates for much of the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the parameter descriptions are unusually rich (mode-specific applicability, priority keys, override rules for search_options). The description adds only credit costs per mode and no parameter-level meaning, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Find domain names and the extensions that fit a business") and enumerates the six modes, so an agent knows this is a domain-sourcing tool rather than a generic search tool. It is clear, but it never contrasts itself with siblings like search or companies, so differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The per-mode credit costs implicitly hint at trade-offs between the heavier suggest-* modes and the cheap lookups, which nudges mode selection, but there is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The schema's mode enum does the real routing work.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does add one genuinely useful behavioral fact: the cost of 2 credits. But it omits whether the lookup requires an exact first/last/domain match, what happens on a miss, and whether results are verified/deliverable — significant gaps for a lookup tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, no waste, with the core purpose front-loaded and the cost constraint immediately following. Nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description should explain what a call yields (matched emails, confidence, no-match behavior). It says nothing about return values or failure modes, leaving the agent under-informed for a paid lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented in the schema. The description adds no syntactic or semantic detail about them (e.g., whether 'company' changes matching behavior), so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource: 'Find professional email addresses.' That is clear enough to act on. However, it offers no differentiation from the sibling 'email-verify', which superficially sounds related, so an agent cannot confidently choose between them from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisite or input expectations, and no mention of alternatives such as 'email-verify' or 'companies'. The agent must infer usage entirely from the name and schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full behavioral burden. It usefully discloses billing ('Cost: 1 credit') and the result categories, but says nothing about permissions, rate limits, latency, whether a credit is charged on failure, or how the verdict is expressed — significant gaps for a zero-annotation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler; the functional outcome is front-loaded and the cost caveat follows. Nothing could be trimmed without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, no-output-schema lookup, the description covers purpose, result categories, and cost, which is nearly everything an agent needs. Only the behavioral layer (failure modes, credit charging rules) remains thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter and schema description coverage is 100%, so the schema already documents 'Email to verify.' The description adds no format, normalization, or validation guidance beyond that, making 3 the appropriate baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (check) and resource (an email) plus the three concrete outcomes it reports: deliverable, catch-all, disposable. That is much stronger than a tautology, but it never distinguishes itself from the nearby 'emails' and 'profiles' siblings, which an agent might confuse with verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use (verify an address before relying on it) is implied by the phrasing but never stated, and there are no exclusions, prerequisites, or alternative tools named. Adequate but leaves the agent to infer when this beat is worthwhile.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It does disclose a genuine behavioral trait, the 2-credit cost, but says nothing about limits, async behavior, error handling for unsupported pairs, or auth requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler; the capability statement is front-loaded and the cost caveat follows. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter conversion tool with no output schema and no annotations, the description conveys capability and cost but omits return shape, size/rate limits, and failure modes for conversion pairs that fall outside the in-house table.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents file_url, source_format (with its full format list) and target_format. The description adds no format syntax, URL requirements, or default-behavior detail beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Convert) and enumerates the resource classes it handles (documents, web pages, spreadsheets, images). No sibling tool overlaps this function, so an agent can route to it unambiguously.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description contains no when-to-use, when-not-to-use, or alternative-tool guidance. It does surface the 2-credit cost, which is a decision factor, but there is no explicit condition for selecting this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. Disclosing "Cost: 3 credits" is genuine value not present in the schema, but the description omits output format (URL vs. bytes), generation latency, sync vs. async behavior, and any content-policy constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences with zero filler, and the core action is front-loaded ahead of the cost note. Nothing here is redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should say what the caller receives (image URL, base64 payload, job ID) and whether the operation is synchronous. It also leaves the 3-credit charge unbounded—no indication whether it is per-image or per-request.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both 'prompt' and 'aspect_ratio' (with its enum and default) are already documented structurally. The description adds no syntax, length, or prompt-engineering guidance, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource: "Generate images from text prompts," which clarifies the ambiguous tool name 'images'. It does not explicitly distinguish itself from other generation siblings (sound-generate, tts, video-download), but the text-to-image purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as bg-remove or screenshot, which also produce images. The only usage-adjacent fact is the credit cost, which is about expense rather than selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses the 3-credit cost, but says nothing about supported inputs beyond the schema, latency, error behavior, or what 'structured data' means as an output. For a paid extraction tool with zero annotation coverage this leaves significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the core purpose front-loaded and the cost noted second. Nothing is wasted or buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, so the description should explain the shape of the returned structured data and any input limits. It instead stops at purpose plus price, leaving the agent without the information needed to interpret results or anticipate failures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter (document_url, 'URL to invoice PDF/image') is fully documented in the schema. The description adds no format or constraint detail, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Extract structured data from invoices and receipts.' The scope (invoices/receipts) is clear and distinguishable from most siblings like transcribe or file-convert. However, it does not explicitly contrast with the closest siblings (documents, scrape), so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus alternatives (documents, scrape, file-convert), no prerequisites, and no exclusions. The only contextual information is the credit cost, which is pricing rather than usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, but it does add one genuinely useful behavioral fact: the 3-credit cost. It says nothing about authentication, rate limits, what happens on a miss, or whether credits are charged per match or per call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, both front-loaded and both earning their place: the purpose first, then the billing constraint. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists and no annotations are supplied, yet the description never says what an enriched profile looks like or even that at least one of the five optional parameters is needed to match anything. For a zero-required-parameter lookup tool with no structured safety or return info, this leaves the agent under-informed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema; the description adds no syntax, format, or combination guidance beyond that. Baseline 3 applies when structured data does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a concrete verb pair (find, enrich) and the resource (professional profiles), so the agent knows it searches and augments people records rather than companies or emails. It stops short of distinguishing itself from siblings like companies or emails or of clarifying what 'enrich' actually returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance, no prerequisites, and no alternatives. With 23 siblings including companies, emails, and search, an agent has nothing telling it whether to reach for this tool or one of those.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the multi-stage pipeline and, unusually helpfully, the per-depth credit cost (10/20/35), which is real behavioral context. It omits latency expectations, failure behavior, and whether partial results are returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core capability and followed by the cost table. No filler; every clause conveys either what the tool does or what it costs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with no output schema and no annotations, the description covers the pipeline, the return artifact (cited report), raw-vs-synthesized behavior implicitly, and pricing. Remaining gaps — runtime, partial-failure behavior, and the scope of the other parameters — are modest given the schema fully documents inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning by mapping cost to the `depth` enum values (standard 10, deep 20, comprehensive 35) — information that exists nowhere in the schema. The other seven parameters (synthesis, max_sources, enrich_entities, etc.) get no elaboration beyond their schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Multi-step deep research') and enumerates the pipeline stages (search, scrape, enrich, synthesize into a cited report), which distinguishes it from thin siblings like search or scrape. It does not name an alternative sibling explicitly, but the pipeline framing makes the composite nature clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for research questions requiring multi-step synthesis, but gives no explicit when-to-use versus alternatives such as search, scrape, or site-intel, and no when-not guidance. An agent must infer that this is the heavyweight option.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It adds genuine behavioral value by disclosing per-mode credit costs, which appear nowhere in the schema, but says nothing about auth needs, rate limits, retry/error behavior, or what happens on blocked pages.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with zero waste: purpose first, cost second. Every clause earns its place and nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters at 100% schema coverage and no output schema, the description is close to sufficient. The credit-cost disclosure is a useful addition, though an agent gets no signal about failure modes or scraping restrictions on a tool that explicitly has anti-bot modes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description adds above-baseline meaning by mapping each mode enum value to a specific credit cost ('fast 1 credit, standard 2, thorough 5') — a mapping the schema does not contain. It does not touch url, output, timeout, or wait_for, but those are already fully documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Extract content from any URL') plus the output formats (Markdown or HTML), so the agent knows exactly what comes back. It is distinguishable from siblings like screenshot or site-intel by its raw-content-extraction framing, though it never names or contrasts with any sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance, and no alternatives named among the 23 sibling tools. The credit-cost line hints at a cheap-vs-expensive tradeoff between modes but gives no rule for choosing the tool itself over search or site-intel.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose the credit cost, which is genuinely useful context an agent cannot get from structured fields, but it says nothing about rendering latency, timeouts, auth requirements, or what happens on unreachable URLs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero waste, action front-loaded and cost appended. Nothing redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter tool with no annotations and no output schema, the description is thin: it never says whether the result is image bytes, an inline image, or a URL, which matters given the absent output schema. The cost disclosure is the one piece of compensating detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters (url, width, height, format, full_page) are already documented with defaults and an enum in the schema. The description adds no parameter-level meaning, which is acceptable at this coverage level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Capture a rendered screenshot of any webpage.' The word 'rendered' usefully distinguishes it from a raw HTML fetch, but the description never acknowledges the nearby sibling 'scrape', so an agent gets no explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no exclusions, no mention of alternatives such as scrape or site-intel. The only contextual note is the per-call cost, which is pricing, not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses credit cost per mode, which is real added context, but says nothing about output format, latency, rate limits, or result structure for a tool whose return shape is undefined by any output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with zero filler, and the mode enumeration is front-loaded ahead of the cost table. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter search tool with fully documented schema but no output schema, the definition covers modes and pricing adequately. The notable gap is that, absent an output schema, it never describes what a result looks like or how many results/services are returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents mode, query, country, freshness, and num_results thoroughly; baseline 3 applies. The cost mapping hints at mode tradeoffs, but the description adds no format or syntax detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search the web') and enumerates its three delivery modes (SERP, AI synthesis, or both). The purpose is unmistakable, but it offers no differentiation from adjacent siblings like research, site-intel, or scrape.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The cost-per-mode breakdown (serp 1, ai 2, deep 3 credits) implicitly guides mode selection toward the cheapest sufficient option. However, there is no explicit when-to-use guidance, no exclusion of alternate tools (research, scrape, site-intel), and no statement of when each mode is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden but does disclose a genuinely useful trait beyond the schema: per-mode credit costs (overview 2, whois 1, dns 1, etc.). It does not say whether the operation is read-only, what permissions/auth are required, or what happens on lookup failure, so transparency is partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the tool's purpose, followed by the capabilities and then the cost table; no filler sentences. The credit list is slightly repetitive with the repeated word 'credits' but remains dense and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter data-gathering tool with no output schema and no annotations, the description should do more to describe the shape of the returned intelligence and any constraints (e.g., can modes be combined, lookup failure behavior). The capability and cost coverage is good, but the return-side context is thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100% and baseline is 3, but the description adds real meaning beyond the schema by mapping each enum value of 'mode' to a credit cost, letting the agent reason about budget when choosing depth. That is value the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Get comprehensive domain intelligence') and enumerates the data classes returned: WHOIS, DNS, SSL, tech stack, email security, hosting. An agent can immediately tell what the tool produces. It does not, however, differentiate itself from potential siblings such as 'domains' or 'scrape', which may overlap in scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use/when-not-to-use guidance and no named alternative among the siblings. The mode list with credit costs does imply a depth-versus-cost selection heuristic, so usage is inferable rather than stated. That places it at minimum-viable rather than clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses a credit cost of 1 and the WhatsApp 24-hour opt-in window, but says nothing about failure handling, delivery confirmation, rate limits, or what happens to the credit if a message is dropped. It covers the notable constraints without giving a full behavioral picture.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, then the default-channel behavior, then the opt-in caveat and cost. Every sentence carries information an agent needs, with no filler or restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter send tool with no output schema, the description covers the essentials: action, channel default, the WhatsApp eligibility constraint, and cost. It does not describe what a successful send returns (message ID, delivery status) or error behavior, which would matter for an agent that must confirm delivery.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so 'to', 'message', and the channel enum are already fully documented in the schema, including the silent-drop warning for WhatsApp. The description's channel comments align with the schema (default 'auto' routes to SMS) but add no syntax or formatting detail beyond it. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description leads with a specific verb and resource ('Send SMS or WhatsApp messages') and immediately scopes the channels supported. None of the listed siblings (email-verify, tts, scrape, etc.) overlaps with outbound messaging, so there is no ambiguity to resolve. An agent knows exactly what this tool does from the first sentence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives real selection guidance between the two channels: SMS is framed as the default and 'reliable delivery', and WhatsApp is conditioned on the recipient having messaged your Business number within 24 hours. What is missing is any statement of when not to use the tool at all, or a pointer to an alternative channel/tool if WhatsApp is unavailable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It adds useful cost context (4 credits), but says nothing about latency, rate limits, whether generation is synchronous, or what the caller receives back.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence covering action, scope, exclusion and cost with zero filler. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter generation tool with no output schema and no annotations, the description covers the critical decision points (scope, exclusion, cost). It is slightly short of complete because it never says what the tool returns — an audio URL, a file, or a job id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so duration bounds, format options and prompt_influence semantics are already documented in the schema. The description adds no parameter detail beyond what is already there (even the NOT-speech note is duplicated in the prompt field).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (generate) and resource (sound effects and short music tracks) from text prompts, and explicitly carves out the boundary with the sibling tool tts for spoken voice. An agent can distinguish it from tts and stt without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the exclusion case (NOT speech, use tts) and the applicable scope (sound effects, short music tracks), which is real routing guidance. It stops short of naming a full when/when-not matrix, but the one alternative that matters is called out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full behavioral burden. It usefully discloses the cost (2 credits), but says nothing about which audio input to supply when both audio_url and audio_base64 are optional, permission/auth needs, size limits, or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the action and appended with the cost. No filler, and both facts are immediately useful to an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should cover the return shape; 'with timestamps' hints at it but doesn't describe the format. It also doesn't resolve the zero-required-parameter input ambiguity, though the cost disclosure is a helpful addition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 and the schema already documents all three parameters. The description adds nothing about the parameters, and notably neither schema nor description explains whether audio_url and audio_base64 are mutually exclusive alternatives.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Transcribe audio to text') plus an output trait ('with timestamps'), which is clear on its own. However, with a sibling literally named 'transcribe' in the same toolset, it does nothing to distinguish itself from that tool, leaving ambiguity about which to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to use this tool versus the 'transcribe' or 'subtitle' siblings, nor any prerequisites. Given the near-duplicate sibling name, the absence of routing guidance is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses the cost (2 credits) and output formats, but omits authentication needs, async behavior, file-size limits, and what the tool actually returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with purpose and followed by a critical cost note. Every sentence earns its place with no wasteful wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core purpose and pricing, and the input schema is fully documented. However, with no output schema present, it does not explain what the tool returns (subtitle text, file URL, etc.) or whether the operation is synchronous, leaving a meaningful gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains all three parameters. The description adds only a general mention of audio/video input and SRT/VTT output, without syntax or format details beyond the schema's own enum and defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: generate SRT/VTT subtitles from audio or video. However, it does not distinguish this tool from nearby siblings like transcribe or stt, leaving the agent to infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no when-not-to-use guidance, and no reference to alternatives such as transcribe or stt. The agent must infer that this is for subtitle generation rather than plain transcription.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose a real behavioral trait: a cost of 3 credits, which lets the agent weigh expense. Beyond that it is silent on auth needs, file-size/duration limits, sync vs. async execution, and what the transcript output looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, capability first and cost last, with no filler or repetition of the tool name. It is efficiently sized, though the brevity is closer to under-specification than to a fully earned five.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter tool with a fully described schema and no output schema, the core is covered, but an agent still lacks the output shape (text? segments with speaker/time?) and cannot tell this apart from 'stt'. With no annotations to fall back on, those gaps matter more.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are already documented in the schema, which sets the baseline at 3. The description's mention of diarization loosely maps to speaker_labels but adds no syntax, format, or default semantics beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (Transcribe) and resource (audio) plus two differentiating features (speaker diarization, timestamps), so the agent knows what it produces. It does not, however, distinguish itself from the sibling 'stt' tool, which plausibly overlaps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, no prerequisites (e.g. URL must be publicly reachable), and no mention of the near-identical sibling 'stt' that an agent would need to choose against. The only implicit context is that this handles audio.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose one genuinely useful non-schema trait: the 2-credit cost. It says nothing about the return format (URL vs. binary), latency, provider fallback behavior when 'auto' is used, or async handling, which are real gaps for an audio-generation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler, and the core action is front-loaded ahead of the cost note. Nothing to trim.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter generation tool with no annotations and no output schema, the description covers the action and cost but leaves the return contract and provider-selection behavior unexplained. Adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents 'text', the provider enum, and 'voice_model'. The description adds no parameter-level meaning, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource ('Convert text to speech audio'), which is immediately distinguishable from the sibling 'stt' (the inverse direction). It does not, however, differentiate itself from 'sound-generate' or 'transcribe', so sibling routing still requires inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus the related audio siblings ('stt', 'sound-generate', 'transcribe'), nor any stated prerequisites. The agent is left to infer that this is the text-in/audio-out path from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full behavioral burden. It usefully discloses the credit cost (3 for video, 2 for audio) and that the returned link is temporary, but says nothing about authentication, rate limits, failure modes, or what happens to the generated file. Partial coverage for a mutation-ish operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the action and outcome, with cost appended as a secondary fact. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly explains the return value (a temporary download link), which is its main burden. However, with zero annotations and a real cost/irreversibility dimension, it omits auth requirements, link expiry behavior, and error handling, leaving notable gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with enums and defaults for format and quality, so the schema already documents the parameters thoroughly; baseline 3 applies. The description adds only indirect value by implying the audio/video cost split (mp3/m4a vs mp4) without tying it explicitly to the format parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Download video from any URL') and even names the return value (a temporary download link). It does not, however, differentiate itself from the sibling 'video-info', which an agent might reasonably confuse with a downloader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, no prerequisites, and no mention of the sibling 'video-info' or 'file-convert'. The agent must infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses a cost of 1 credit, but says nothing about permissions, rate limits, site support, or failure behavior for unsupported URLs. That cost note is real added value, but the disclosure is thin for a tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with zero filler; the extraction scope is front-loaded and the cost note is appended last. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read tool with no output schema, the description tells the agent what comes back (metadata, formats, thumbnail) and what it costs, which is most of what is needed. Missing only guidance on unsupported URLs or prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter has 100% schema description coverage, so the schema already documents the url field. The description's 'from any URL' adds only marginal scope information and no format or syntax detail. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a clear verb (Extract) and enumerates the resources returned: metadata, available formats, and thumbnail. It implicitly distinguishes itself from the sibling video-download (info vs. fetching the file), but never names an alternative, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied — an agent can infer this is the pre-download inspection step, but there is no explicit when-to-use, when-not, or routing to siblings like video-download or subtitle. Adequate but leaves the trigger condition to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.