Suprsonic

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 add real value by disclosing the output format (transparent PNG) and a credit cost, but it says nothing about permissions/auth needs, rate limits, input format/URL accessibility constraints, or expected latency.

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, front-loaded sentences: purpose first, then output, then cost. Zero filler and nothing is 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 simple 2-parameter tool with full schema coverage and no output schema, the description covers the essentials and even compensates for the missing output schema by naming the return artifact. It falls short only on input constraints (accepted image formats, URL size limits) and failure behavior.

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 enum auto/small/hd) are already documented in the schema. The description adds no meaning beyond that, which matches the baseline of 3 for fully-covered schemas.

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 ("Remove background from any image") and additionally nails down the output ("transparent PNG") and cost ("2 credits"). An agent immediately knows what this tool does and what it produces; no sibling tool overlaps with this capability.

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: the tool applies to "any image" reachable by URL. There is no statement of when to prefer it over alternatives (e.g., images or file-convert), no prerequisites, and no exclusions or limits on acceptable inputs.

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 that execution is sandboxed and that it costs 2 credits, but says nothing about whether the sandbox has network access, whether state persists between calls, what happens on timeout, or what the 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, front-loaded sentences with zero waste; the core action leads and the cost constraint follows.

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 mutation-ish tool with no annotations and no output schema, the definition is thin. It omits return values, failure/timeout behavior, and side-effect semantics that an agent would need before submitting code.

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 parameters, defaults, and enum values are already fully documented in the schema. The description's mention of 'pre-configured environments' loosely maps to the template parameter but adds no new syntax or meaning 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 (Execute) and resource (code) plus the execution environment (secure sandbox, pre-configured environments). No sibling tool overlaps with code execution, so sibling differentiation is moot, but the description never says what the sandbox can/cannot do.

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 prerequisites, and no statement of when this tool should be preferred over alternatives. The only extra context is a cost note, which is not selection 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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses a concrete cost (3 credits), which is real value beyond structured fields, but says nothing about what the enrichment returns, auth requirements, or rate limits.

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 the operation front-loaded and the cost constraint following. Every word earns its place; nothing is padded or redundant.

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 must convey what an agent gets back from an enrichment call, and it does not. Whether it returns firmographics, employee counts, or revenue is left entirely unknown, which is a meaningful gap for this tool type.

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 (domain, company_name) are already documented in the schema, establishing a baseline of 3. The phrase 'by domain' merely reinforces the required param and adds no syntax, format, or fallback detail beyond it.

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 (enrich), a specific resource (company data), and the keying mechanism (by domain), which an agent can distinguish from generic siblings like search or scrape. It stops short of naming or contrasting any actual sibling tool, so 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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The only usage-adjacent content is a cost note, which is a budgeting hint rather than an invocation rule.

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 must carry the full burden. It discloses cost (3 credits) which is helpful for budgeting, but says nothing about rate limits, permissions, or that it returns structured data according to the given schema. It is a mutation-like operation (extraction) with no safety profile disclosed.

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 purpose, followed by cost. No wasted words.

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 tool with four parameters, including a nested schema object, no annotations, and no output schema, the description is minimal. It omits how the 'schema' parameter interacts with 'extraction_prompt', what happens if both are provided, and what the output will be, leaving the agent to infer critical behavior.

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 fully documents each parameter. The description adds only the cost information, not parameter semantics. 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?

States a clear action ('Extract structured data') and input sources ('URLs or content'). However, the tool name 'documents' is opaque and doesn't clearly map to the extraction purpose, and the description doesn't distinguish it from siblings like 'scrape' or 'research' which also handle web content.

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 is given about when to use this tool versus alternatives such as 'scrape' (which likely fetches content) or 'research'. The relationship to scrape is implied only by the 'Pre-scraped text content' param, leaving the user to infer that this tool is for extraction, not scraping.

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 contribute genuinely useful non-schema information: per-mode credit costs. That is real transparency value. However, it omits return shape, whether operations are read-only, rate limits, and pagination behavior, so it is only 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?

Two tight sentences with the purpose front-loaded and the cost data packed into a single scannable clause. No filler; every element earns its place. Slightly dense cost enumeration but well structured.

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, six-mode tool with nested objects and no output schema or annotations, the description omits mode-selection guidance and any sense of what each mode returns. The rich per-parameter schema descriptions partly compensate, but the description itself leaves meaningful 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% and each parameter is already tagged with the mode(s) it applies to (tlds, query, domains, purpose, search_options, etc.), so the schema does the heavy lifting. The description adds little parameter meaning beyond restating the mode names in the cost list. 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?

States a specific verb and resource — 'Find domain names and the extensions that fit a business' — and the cost sentence enumerates the six mode capabilities (suggest-names, suggest-extensions, search-extensions, check-availability, pricing, tlds). It is clear about scope, though it describes the suggest-* flavor well while the pricing/tlds/availability modes are named only as line items rather than explained.

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 is offered. The description never says which mode to pick for a given intent, nor does it point to any alternative; the sibling list (search, site-intel) is not referenced. An agent must infer mode selection entirely from the 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 are provided, so the description carries the full behavioral burden. It usefully discloses the cost (2 credits), which is real behavioral context an agent needs. However, it says nothing about whether credits are spent on failed lookups, whether results are verified for deliverability, or what format is 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 short sentences, zero waste, with the core purpose front-loaded ahead of the cost note. 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?

With no annotations and no output schema, the description should carry more: what a successful result looks like (verified address? confidence?), and how it relates to email-verify. Parameter documentation is fully covered by the schema, so the gap is in behavior and returns.

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; only 'domain', 'company', 'last_name', and 'first_name' exist and the schema explains each. The description adds no parameter meaning (e.g. required vs optional combinations), 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 and resource: finding professional email addresses. This distinguishes it from most siblings like domains or profiles, though it never explicitly separates itself from the closely-related email-verify sibling.

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 email-verify, no prerequisites, and no stated conditions (e.g. when a lookup will fail). The only qualified guidance is the price, which is 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 a cost of 1 credit, which is a genuine behavioral trait absent from the schema, but it omits whether verification is a passive lookup or an active SMTP probe, whether it sends anything to the address, and how reliable catch-all detection is. Partial disclosure only.

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 capability and followed by the cost constraint. Every sentence carries information; nothing is padding.

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, but the description enumerates the possible verdicts (deliverable, catch-all, disposable), effectively sketching the return values, and the credit cost is stated. For a single-parameter, no-annotation tool this is nearly sufficient, though accuracy/latency expectations remain unstated.

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 ('Email to verify'), so the schema already documents it fully. The description adds no syntax, format, or normalization guidance beyond what the schema provides, which is the expected 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?

The description gives a specific verb (Check) and resource (email) plus the exact result categories it distinguishes: deliverable, catch-all, disposable. That is far more informative than a tautological restatement. It doesn't explicitly differentiate itself from the sibling 'emails' tool, so it falls 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?

There is no guidance on when to reach for this tool versus alternatives like 'emails' or 'profiles', and no prerequisites or exclusions are stated. Usage is only implied by the tool's name and stated outcome categories.

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 one concrete trait — a 2-credit cost — which is real value beyond the schema, but it says nothing about permissions, limits, failure modes, or what a successful conversion 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 the core action and followed by the cost. Every sentence earns its place with 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?

For a 3-parameter conversion tool with no annotations and no output schema, the description covers what it does and its cost but omits anything about the return value (URL, binary, file handle) or error behavior. Given the schema handles parameters well, this is adequate but leaves an obvious gap around output.

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 fully documents file_url, source_format (with its enumerated values) and target_format (with default and ConvertAPI fallback). The description adds no parameter-level meaning beyond restating the resource categories, 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?

States a specific verb+resource ('Convert documents, web pages, spreadsheets and images between formats') and names the input categories, which is precise enough to distinguish it from the sibling tools (none of which is a format converter). It stops short of 5 because it doesn't explicitly contrast itself with adjacent siblings like images or screenshot.

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/when-not guidance and names no alternatives. An agent must infer from the sibling list that no other conversion tool exists. The only usage-adjacent content (the ConvertAPI routing note) lives in the schema, not the description.

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 discloses only the credit cost. It omits whether generation is synchronous or polling-based, how the artifact is returned (URL vs. inline data), how long results persist, and whether prompts are moderated — all material for an image generator.

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 capability and immediately followed by the cost. Every word earns its place with 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 should explain what comes back and how to consume it; it does not. For a generation tool with no annotations and no return-value documentation, the cost line alone is not sufficient for confident invocation.

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 (prompt, aspect_ratio) are already documented with enum values and a default. The description adds no extra meaning, but the baseline of 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 states a specific verb and resource ("Generate images from text prompts"), which is immediately actionable. It does not, however, differentiate itself from adjacent generation siblings such as sound-generate or tts, so an agent must infer the boundary from the noun 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 guidance on when to use this versus alternatives, no prerequisites, and no mention of limits or iteration. The only contextual detail is the credit cost, which speaks to budget 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?

With no annotations, the description carries the full behavioral burden, and it discloses only the credit cost (3 credits), which is genuinely useful operational context. It says nothing about input constraints (file size, page limits, supported formats), latency, failure behavior, or what happens on an unreadable document.

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: purpose first, cost second. 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?

There is no output schema, so the return value is entirely on the description — yet it never indicates what structured fields are extracted or in what shape, which matters for a parsing tool. Cost and purpose are covered, but that gap plus absent input constraints keeps it only adequate.

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?

One required parameter with 100% schema description coverage, so the schema already explains document_url fully as a URL to a PDF/image. The description adds no syntax, size, or format guidance beyond that, which is the expected baseline when the schema does the work.

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 (extract) and resource (structured data from invoices and receipts), which an agent can clearly distinguish from generic siblings like documents or scrape. It stops short of naming an alternative or bounding scope, but the purpose itself 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 conditions, no named alternatives. The only routing signal is implicit ('invoices and receipts'), so an agent must infer when this beats documents or scrape on its own.

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 only discloses the 3-credit cost. It does not state whether this is a read-only lookup, how enrichment behaves if a profile is not found, whether calls are idempotent, or what a successful/cached lookup 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 with zero filler, and the operational purpose is front-loaded before the cost note. It is terse to the point of under-specification, but 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?

There is no output schema and no annotations, and five optional parameters mean the agent must guess how inputs combine and what the enriched payload contains. For a dual-purpose (find + enrich) tool with cost implications, the description omits too much to call it complete.

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 are already documented in the schema. The description adds no format hints (e.g., LinkedIn URL matching, name normalization) or guidance on which identifiers work best, 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?

"Find and enrich professional profiles" gives a specific verb pair (find/enrich) and a clear resource (professional profiles), which distinguishes it from lookup siblings like companies or emails. It stops short of naming how it differs from adjacent tools such as search or scrape, so it is clear but not fully differentiated.

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 indication of when to choose this over siblings like companies, emails, or search, and no prerequisites or input-combination rules. The only usage-relevant signal is the credit cost, which hints at cost-sensitivity but does not guide tool 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 research pipeline and credit costs, but omits read-only/destructive nature, latency, auth requirements, rate limits, and failure 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 sentences, front-loaded with the tool's purpose and then the cost schedule. Every sentence earns its place with 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?

For an 8-parameter research tool with no annotations and no output schema, the description conveys process, output type, and cost. However, it lacks usage boundaries and operational expectations, leaving important context 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 coverage is 100%, giving a baseline of 3. The description adds meaningful depth-cost mapping (standard 10, deep 20, comprehensive 35) that is not present in the schema and directly informs the depth parameter choice.

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 multi-step verb and resource: search, scrape, enrich entities, and synthesize into a cited report. This distinguishes it from single-step siblings like search, scrape, and companies.

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 use for multi-step deep research, but does not explicitly say when to choose it over search/scrape or when not to use it. Cost tiers help select depth, but alternative selection guidance is absent.

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 costs per mode, which is nontrivial behavioral context, but it omits other important traits such as read-only safety, rate limits, authentication requirements, and failure 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 tight sentences with no filler. The core purpose is front-loaded and the cost detail follows immediately.

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?

Given 5 parameters, no output schema, and no annotations, the description is reasonably complete when combined with the fully documented schema. It states output formats and costs, though it could say more about return structure and when to prefer this tool over siblings.

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. The description adds meaningful parameter context by mapping modes to credit costs, though it does not cover every parameter detail.

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 names a specific verb and resource: 'Extract content from any URL as Markdown or HTML.' This is clear and not tautological, but it does not distinguish the tool from siblings such as screenshot, site-intel, or search.

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 provides no guidance on when to use this tool versus alternatives like screenshot, search, or site-intel. The cost information helps choose a mode, but not whether to choose this tool at all.

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 supplied, the description carries the full behavioral burden. It does disclose the credit cost ('Cost: 1 credit'), which is genuinely useful and not derivable from the schema, and 'rendered' hints that JavaScript executes. However, it says nothing about auth requirements, rate limits, rendering wait behavior, or what form the result takes.

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, purpose first, cost second. Nothing is padded or restated from the name, and the key constraint is front-loaded.

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, so the description ideally would indicate whether the caller receives an image payload or a URL, and no annotations cover safety or mutation profile. For a simple one-shot capture tool the gap is modest, but the return shape and cost semantics (per-call vs per-page, authentication) remain unaddressed.

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 in the schema with defaults and an enum for format. The description adds no parameter-level detail beyond that, 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 ('Capture a rendered screenshot of any webpage'), which clearly separates it from content-returning siblings like scrape or search. It does not name or compare itself to any sibling, so the differentiation is inferential rather than explicit.

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 choose this tool over alternatives such as scrape (content vs visual) or images (processing vs capture). The only usage-adjacent statement is a cost note, which is a budget fact rather than a when-to-use rule.

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 disclose a genuinely valuable behavioral trait — credit cost per mode (1/2/3) — but says nothing about auth requirements, whether the call is read-only, rate limits, or that results reflect live web data. Disclosing cost alone leaves meaningful behavioral 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, and the core action is front-loaded ahead of the cost detail. 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 tool with no annotations and no output schema, the description is adequate but thin: parameters are covered by the schema, yet the agent gets no sense of return shape (raw links vs synthesized answer) or how this differs from the many sibling search-ish tools. Minimum viable rather than complete.

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. The description goes slightly beyond the schema by mapping each mode value to its credit cost, which directly informs the mode parameter tradeoff — a real addition even though country, freshness, and num_results are left entirely to 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 (search) and resource (the web) and names the three selectable modes (SERP, AI synthesis, both). However, it gives no differentiation from plausible siblings like research, scrape, or site-intel, so an agent cannot tell from the description alone why it would pick this tool over those.

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 line gives an implicit decision rule (cheaper raw SERP vs pricier synthesis), which is useful. But there is no explicit when-to-use/when-not guidance and no pointer to the overlapping siblings (research, scrape), leaving mode/alternative selection 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 burden, and it does disclose a real behavioral trait: credit cost per mode (overview 2, whois 1, dns 1, tech-stack 2, security 2, subdomains 2). It says nothing about rate limits, authentication, caching, or whether results are live vs cached, which is a meaningful gap for an un-annotated 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 tight sentences: the capability list comes first, followed by the cost table. No filler, and every token in the cost enumeration maps to a real decision (which mode to spend credits on).

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 adequately conveys what data comes back and what each mode costs, which is what an agent needs to invoke it correctly. It stops short of covering auth, rate limits, or how it differs from the sibling 'domains' 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 baseline is 3, but the description adds genuine meaning by mapping each enum mode to its credit cost, which the schema does not convey. It also clarifies that the default overview mode is the broader, more expensive aggregate.

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 ('Get') and resource ('domain intelligence') and enumerates the exact data categories returned (WHOIS, DNS, SSL, tech stack, email security, hosting). However, it never distinguishes itself from the sibling 'domains' tool, so an agent must guess which of the two to pick for domain lookups.

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 cost list implicitly guides mode selection, but there is no explicit when-to-use guidance, no exclusions, and no mention of the overlapping 'domains' sibling. Usage is inferable from the mode/cost table rather than stated.

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 burden well: it discloses the default channel, the WhatsApp opt-in precondition with its 24-hour window, the silent-drop risk, and the 1-credit cost. It omits failure/error behavior for the SMS path and any rate limits or throughput notes.

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 compact sentences with no filler, front-loading the core action and default before the conditional WhatsApp caveat and the cost note.

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?

Covers cost, channel defaults, and the main precondition for a tool with no annotations and no output schema. It would be stronger if it said what a successful send returns (message id, delivery status) since no output schema exists to describe the response.

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%, including a full enum description for channel that already covers opt-in and silent dropping, so the schema does most of the work. The description's added nuance is limited to calling SMS 'reliable delivery'; 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?

States a specific verb (send) and resource (SMS/WhatsApp messages), and the channel scope is clear from the first sentence. It is inherently distinct from siblings like emails or tts, though it does not explicitly name any sibling to contrast against.

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?

Gives clear channel-selection guidance: SMS is the default and reliable, WhatsApp requires opt-in within 24 hours. It does not mention when to prefer a sibling tool (e.g., emails) instead, but the when-to-use-each-channel guidance is explicit.

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 provided, the description carries the full behavioral burden. It usefully discloses the monetary cost ('4 credits') and the non-speech scope, but it omits other important traits such as authentication needs, rate limits, storage side effects, and whether generation is synchronous or asynchronous.

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?

The description is two compact clauses with no wasted words. The primary purpose and the key exclusion are front-loaded, and the cost is placed efficiently at the end.

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 explain return values or result behavior, but it does not state what is returned (e.g., audio URL, file, or inline data) or whether generated audio is stored. It covers purpose, exclusion, and cost, but leaves return semantics and side effects unstated.

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 prompt, output_format, duration_seconds, and prompt_influence in detail. The description does not add parameter-level meaning beyond what the schema provides, making the baseline score of 3 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 ('Generate'), specific resources ('sound effects and short music tracks'), and input type ('text prompts'). It also explicitly distinguishes this tool from the speech-specific sibling by saying 'NOT speech: use tts for spoken voice.'

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 directly tells the agent when not to use this tool ('NOT speech') and names the correct alternative ('use tts for spoken voice'). For the relevant audio-generation scenario, the when-to-use case is clear from the first phrase.

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 only discloses pricing ('Cost: 2 credits'). It says nothing about whether audio_url and audio_base64 are mutually exclusive (both are non-required, which is ambiguous), supported formats or duration limits, authentication needs, or failure 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 short sentences with zero filler, and the core capability is front-loaded ahead of the cost note. Nothing here is 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?

No annotations and no output schema exist, yet the description omits the things an agent actually needs: input-mode selection between URL and base64, format/size limits, duration caps, and any sense of the response payload beyond 'timestamps'. For a 3-parameter tool with ambiguous required fields, this is too 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 description coverage is 100%, so each parameter is documented in the schema itself and the baseline is 3. The description adds no parameter meaning beyond that — notably it does not clarify that the two audio inputs are 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?

States a specific verb and resource ('Transcribe audio to text') plus an output trait (timestamps), which is clear on its own. However, no sibling differentiation is offered even though the sibling list contains a 'transcribe' tool, so an agent cannot tell from the description alone which one 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 when-to-use guidance, no prerequisites, and no mention of the overlapping 'transcribe' sibling. The agent gets no help deciding between stt, transcribe, or subtitle.

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 2 credits, but omits whether the operation is synchronous, expected processing time, whether the audio is retained, and where/how the subtitle file is delivered.

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, the core action is front-loaded and the cost note follows. No wasted words.

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, the description should explain the return value (file, URL, or inline text) and any constraints such as supported input size or duration. It provides none of this, leaving a generation tool underspecified for correct invocation interpretation.

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 each parameter (format, language, audio_url) is documented in the schema with defaults and an enum. The description adds no extra meaning beyond the schema, 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?

The description states a specific verb (Generate) and resource (SRT/VTT subtitles) with the input mediums (audio or video), which is clear enough to distinguish it from most siblings. However, it does not disambiguate from closely related siblings like 'transcribe' and 'stt', leaving overlap for an agent to resolve.

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 choose this over 'transcribe' or 'stt', nor any prerequisites or exclusions. The only supplemental context is a cost note, which is 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 disclosure burden. It does add genuinely useful behavior: the credit cost and the fact that output includes diarization and timestamps. It omits format/size limits and whether the call is synchronous, leaving real gaps for a media-processing 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 punchy sentences with zero filler; the core capability leads and the cost caveat follows immediately. Nothing to trim 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?

No output schema and no annotations means the description must carry behavior on its own. Cost and output features are covered, but for a 3-parameter media tool it says nothing about supported formats, limits, or latency, so an agent lacks key operational context.

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 (language, audio_url, speaker_labels) are documented in the schema. The description's mention of diarization loosely maps to speaker_labels but adds no syntax or format detail beyond the schema, 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 (Transcribe) and resource (audio) plus distinguishing features: speaker diarization and timestamps. However, the sibling list contains 'stt', which almost certainly overlaps with transcription, and the description makes no attempt to differentiate itself from that tool.

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 and no mention of the obvious alternative sibling ('stt'). The only selection signal is the credit cost, which a user might weigh, but the description never says when to choose this over stt or subtitle.

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 the credit cost ('Cost: 2 credits'), but does not describe the return format, authentication needs, rate limits, or whether the audio is returned inline or as a link. This is a minimum viable disclosure with clear 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, front-loaded sentences with zero waste. The core action comes first, followed by the cost, making it easy for an agent to scan and act on.

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 low-complexity conversion tool with 100% schema coverage, the description covers the purpose and cost. However, with no output schema and no annotations, it leaves return behavior and usage context unstated. 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, provider, and voice_model with descriptions and an enum. The description adds no additional parameter meaning beyond what the schema provides. 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 states a specific verb and resource: 'Convert text to speech audio.' It is immediately clear that this is a TTS tool and not its sibling stt (speech-to-text), although it does not explicitly name or exclude any alternatives. Clear, but no sibling 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?

The description gives no when-to-use guidance, prerequisites, or alternatives. It does not mention when to choose tts over sound-generate or other audio siblings, nor when not to use it. Usage is only implied by 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 the full burden. It usefully discloses the credit cost (video 3, audio 2) and that the result is a temporary link, but omits link expiry duration, rate limits, size/duration caps, and error behavior for unsupported 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 tight sentences with the core action front-loaded and cost information 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 tool with no annotations and no output schema, the description covers the action and return type but leaves key operational details (link validity window, credit refund behavior on failure, capability limits) unspecified.

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 schema already documents url, format, and quality with defaults and enum values. The credit line implicitly distinguishes video (mp4) from audio (mp3/m4a) formats, adding slight value, but overall 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?

States a specific verb and resource ('Download video from any URL') plus the return artifact ('temporary download link'). It clearly distinguishes itself from unrelated siblings like tts or transcribe, but does not name the closest sibling video-info, which the agent must infer is for metadata rather than downloading.

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 and no exclusions. The agent is not told to prefer video-info for metadata first, nor given prerequisites (e.g., supported platforms, whether a paid plan is required) that would route it correctly.

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 a real behavioral trait beyond the schema — the 1-credit cost — which is genuine value, but says nothing about supported platforms, failure modes, auth requirements, or rate limits.

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 capability statement front-loaded before the cost note. Nothing could be removed 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 simple one-parameter, no-output-schema tool, the description usefully enumerates the return payload (metadata, formats, thumbnail) and the cost. The remaining gap is site coverage and error behavior, which an agent would want before calling it on arbitrary URLs.

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 single url parameter is fully documented in the schema itself. The description adds no format examples or constraints (e.g. post URLs vs direct streams) beyond what the schema already says.

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?

Specific verb (Extract) plus concrete resources (metadata, available formats, thumbnail) that distinguish it from the closest sibling, video-download. However, it never names video-download or explicitly frame itself as the read-only informational counterpart, leaving the differentiation implicit.

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 mention of when to prefer video-download instead, and no prerequisites (auth, supported sites). The agent must infer the info-vs-download split from the tool names alone.

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