Found17

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), so the bar is lower, yet the description adds genuinely new context: it returns source-backed fields, differences, missing data and 'comparable prices without inventing values', and it discloses the production auth/billing requirements (x402 v2 PAYMENT-SIGNATURE on Base mainnet USDC, or Stripe billing headers). That auth disclosure is exactly the kind of behavioral detail annotations cannot carry.

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 payment mechanics, with no filler. The second sentence is dense with headers and identifiers, but every token is operational information an agent needs rather than 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?

An output schema exists so return values need not be described, and payment/auth is fully covered. However, the tool exposes four parameters with zero schema descriptions and zero enum explanations, and the description never mentions the 2–6 URL bound or what response_mode changes — the largest gap for a tool of this complexity.

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 0% across four parameters, so the description must compensate and it does not. It alludes to 'multiple product pages' (urls) and 'comparable prices', but gives no meaning for select, max_age_ms (a cache/age bound) or the minimal/standard/evidence response_mode enum, leaving three of four parameters semantically opaque.

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 — 'Compare multiple public product pages' — and adds the bounding constraint. No sibling tool (source_snapshot, web_to_product, website_audit) performs comparison, so an agent can distinguish this tool from the rest of the set 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?

'in one bounded call' implies this is the batch/comparison path rather than a single-page fetch, and the payment sentence implies a production context, but the description never states when NOT to use it or names an alternative tool. Usage is inferable but not spelled 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?

Annotations already declare readOnly/openWorld/idempotent, so the safety profile is covered. The description adds real value beyond that: it discloses that output is bounded, that returned content must be treated as untrusted data rather than instructions, and the exact production payment/auth headers required. It stops short of stating rate limits or caching 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, both front-loaded with the operative facts: purpose and safety warning first, payment mechanics second. The payment sentence is dense with header names but every token is load-bearing for invocation.

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 presence of an output schema means return values need not be explained, and the payment/auth context is well covered. However, for a 6-parameter tool at 0% schema coverage, the description leaves most parameter semantics undocumented, so it is only adequate 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 0% across 6 parameters, so the description carries the full burden and mostly fails. It only gestures at known_content_sha256 and bounded size; it says nothing about include, max_age_ms, response_mode, or the url constraints, leaving four parameters semantically undocumented.

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 (fetch) and resource (bounded public webpage snapshot), and names two distinguishing traits: a content hash and a caller-controlled change check. It is not tautological, though it never names a sibling to contrast against the watch/verify tools.

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 guidance. The 'caller-controlled change check' phrase hints that known_content_sha256 exists for change detection, but the description never says when to prefer this one-shot snapshot over source_watch_check, source_watch_status, or web_qa.

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?

Annotations declare readOnlyHint=false, idempotentHint=false and openWorldHint=true; the description adds a genuinely useful behavioral disclosure that the result is a response-body hash comparison rather than a semantic diff. That resolves output interpretation, but it never explains why the call is non-read-only/non-idempotent (it presumably triggers a live fetch and mutates watch state) or what auth the token represents.

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 action front-loaded and the semantic caveat immediately after; every clause carries information 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?

An output schema exists, so return structure need not be restated, and the hash-vs-semantic-diff note covers the key interpretation question. Still missing for a live external check with loose annotations: the token's purpose/auth requirement and what side effect makes it non-idempotent.

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 0% for both parameters. The description implies watch_id's meaning ('a previously created watch') but says nothing about the required 64-hex token, its role as an auth/ownership credential, or the uuid format expectations, leaving half the parameter surface unaddressed in both schema and prose.

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: it checks a previously created public-source watch, which clearly separates it from source_watch_create/delete/status by the 'previously created' scoping. It does not, however, explicitly contrast itself with source_watch_status, so the agent must infer the difference between an immediate check and a status lookup.

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?

'immediately' implies the tool is used when you want a fresh check rather than a cached/stored state, and 'previously created' implies source_watch_create must have run first. No explicit when-not or alternative-naming guidance is given, so usage is only implied.

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?

The description adds real value beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) by disclosing that the call returns a secret token, that the token must be stored securely, and that the watch is polled for hash changes. It stops short of covering rate limits, auth requirements, or interval 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 tightly packed sentences with no filler. The core action is front-loaded and the token-handling instruction 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?

An output schema exists, so return-value explanation is not strictly required, and the description still usefully flags the secret token. What is missing for a stateful create tool is any guidance on the interval/expiry parameters or polling cadence, which the agent must derive from the schema alone.

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 0% and none of the three parameters (url, interval_seconds, expires_in_seconds) are mentioned by name. 'Time-bounded' marginally gestures at expires_in_seconds, but the 900s minimum and 86400s maximum constraints, and the required URL, 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?

The description gives a specific verb and resource: 'Create a time-bounded watch for a public HTML or text source.' The verb 'Create' naturally separates it from siblings like source_watch_check, source_watch_status, and source_watch_delete, though no sibling is named 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?

Usage is implied by 'time-bounded watch' and the follow-up instruction to 'poll the watch for hash changes,' which hints at the downstream check flow. However, there is no explicit when-to-use/when-not guidance or named alternative, so an agent must infer the workflow.

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?

Annotations already declare readOnlyHint=false and idempotentHint=true, so repeat-delete safety and mutation status are covered structurally. The description adds one genuine behavioral detail beyond annotations – that future checks are cancelled – but omits whether deletion is permanent, whether gathered results are removed, and what the token requirement implies for authorization.

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 with zero filler; the destructive action and its side effect are stated 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?

An output schema exists, so return values need not be described, and annotations carry the safety profile. However, for a destructive two-parameter tool with 0% parameter coverage, the description leaves gaps around authorization (token), irreversibility, and whether previously collected data survives deletion.

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 0% and the description does not mention either parameter. Neither watch_id nor token is explained in prose, so an agent gets no semantic guidance on what identifier to supply or why a 64-hex token is required, despite the low schema coverage demanding compensation.

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 (delete) plus resource (previously created public-source watch) and even the consequence (cancel future checks). An agent can distinguish it immediately from source_watch_create, source_watch_check, and source_watch_status without opening any 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?

The phrase 'previously created' implies the watch must already exist, giving implied usage context, but there is no explicit when-to-use guidance, no mention of alternatives (e.g., source_watch_status to verify before deleting), and no stated prerequisites.

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?

The annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false. The description adds useful behavioral context beyond that by clarifying that it reads status only and does not fetch the source content.

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 a single, front-loaded sentence with no wasted words. It states the core action and its most important constraint 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?

For a simple read-status tool with an output schema and safety annotations, the description covers the essential behavior. However, with both parameters required and 0% schema description coverage, it should at least clarify the role of the token to be fully 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 0%, so the description must carry parameter meaning. It implies watch_id refers to a previously created watch, but it says nothing about the required token, its purpose, or its relationship to authentication, leaving a substantial gap.

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: 'Read the status of a previously created public-source watch.' It also distinguishes the tool from related source-fetching siblings by saying 'without fetching the source,' so an agent can tell it apart from source_watch_check.

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 phrase 'without fetching the source' gives clear context for when to use this tool rather than a source-fetching sibling, but it does not explicitly name the alternative or state exclusions. The context is clear enough for selection, though not fully spelled 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?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description usefully adds that it checks public sources and returns limitations alongside evidence, plus concrete authentication/billing requirements (x402 v2 PAYMENT-SIGNATURE vs. Stripe headers), which is real behavioral context an agent needs before calling.

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: the purpose is front-loaded and the payment mechanics follow. The payment sentence is dense and acronym-heavy but every clause carries required operational 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?

An output schema exists, so return values need not be explained, and billing is covered. However, with four undocumented parameters, an enum-bearing response_mode, and no routing guidance against siblings, the definition is thinner than the tool's complexity warrants.

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 0% across four parameters (claim, source_urls, max_age_ms, response_mode), and the description explains none of them. The billing header names do not correspond to schema parameters, so the description does not compensate for the coverage gap at all.

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 ('Check whether supplied public sources establish a claim') and names the return content ('evidence and limitations'). It is distinguishable from siblings like source_snapshot or web_qa, though it does not explicitly contrast itself with them.

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 siblings such as web_qa or source_watch_check, and no prerequisites beyond billing mechanics. The only usage instruction concerns payment, not task 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?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds significant operational context by specifying production payment mechanisms (x402 v2 PAYMENT-SIGNATURE for Base USDC or X-Found17 billing headers), which is critical for correct invocation and goes beyond the annotations.

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 tight sentences. The purpose is front-loaded, and the payment details, while dense, are necessary for invocation and contain 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?

The tool has three parameters with no schema descriptions, and an output schema exists so return values need not be explained. However, the description omits parameter semantics and usage guidelines relative to siblings, leaving the agent under-informed about when and how to use the tool correctly.

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 0% and the description does not mention any parameters. It adds no meaning beyond the schema for url, max_age_ms, or response_mode, leaving the agent to infer the purpose and acceptable values of each 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?

The description names a specific verb ('Run'), resource ('remote HTTP/HTML/SEO/accessibility checks'), and scope ('public webpage'), which is more precise than a generic audit. However, it does not explicitly differentiate itself from the sibling website_audit, so an agent must still infer which tool to choose.

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 provides no guidance on when to use this tool instead of alternatives such as website_audit or verify_claim. It only explains payment modes, leaving usage context and exclusions entirely 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?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context by specifying that fixes are returned deterministically prioritized and by detailing required production payment/authentication headers, though it omits rate limits and non-production 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 with the purpose front-loaded and no filler. The payment sentence is dense but earns its place if production billing is required.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, the description leaves all three parameters except url unexplained and provides no usage context relative to siblings, making it incomplete for a tool with 0% schema description coverage.

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 0%, so the description must compensate, but it only implies the 'url' parameter via 'one public webpage'. It gives no meaning for max_age_ms or the response_mode enum values (minimal, standard, evidence).

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 ('Audit'), resource ('one public webpage'), and output ordering ('highest-priority deterministic fixes first'). It does not explicitly distinguish itself from siblings such as web_qa or verify_claim, so it falls short of the top score.

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 tool versus alternatives like web_qa, verify_claim, or source_snapshot. The payment information explains billing, not usage context or exclusions.

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?

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuine value beyond them: the 'never invents missing fields' guarantee and the concrete auth/billing paths (x402 PAYMENT-SIGNATURE vs. Stripe headers). It does not cover caching/TTL behavior implied by max_age_ms or failure modes on non-product 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 sentences, front-loaded with the core action; the dense payment clause is functional rather than filler. The billing detail is arguably over-specific for a tool description, but it is actionable and placed after the purpose.

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?

An output schema exists, so return values need no explanation, and the annotations plus auth notes cover the operational envelope. However, with 0% schema coverage the unexplained select/response_mode/max_age_ms parameters and the absent routing guidance leave real gaps for correct 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 0% and the description explains none of the four parameters. 'Selected product fields' loosely gestures at select, but max_age_ms (cache control) and response_mode (minimal/standard/evidence) are left entirely unexplained, forcing the agent to guess at their meaning and interaction.

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: 'Extract selected product fields from a public product page.' An agent can distinguish this from compare_products or website_audit by the resource (a product page) and output (product fields). It stops short of explicitly naming which sibling to use instead for adjacent tasks.

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. Nothing says when to prefer this over web_qa, compare_products, or website_audit, nor what preconditions apply (e.g., page must be a public product page, not a listing page). The payment sentence addresses billing, not task selection.

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