Sewlore Measurement Reference

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond them by disclosing the return format (markdown) and that the content embeds followable links for navigation, which affects how an agent should proceed after the call. It does not discuss failure behavior for invalid URLs, which keeps it below 5.

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

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

Front-loads what it does, then when to use it, then the sibling contrast. Four sentences without redundancy, though the example URL is somewhat expendable given the parameter description.

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

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

For a one-parameter read tool with full annotations, the description covers purpose, usage, return format and follow-up navigation. Only error/empty-page behavior for non-existent URLs is absent, a minor gap.

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

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

Schema coverage is 100% and the single url parameter is documented as 'The URL of the page to fetch'. The description adds only a concrete example URL shape, which is marginally useful but not required 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 and resource (fetch full markdown content of a documentation page) and immediately names the sibling it differs from. An agent can distinguish getPage from searchDocumentation without opening either 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?

Gives an explicit trigger (you have a page URL and want to read its content) and an explicit routing rule against the alternative: searchDocumentation returns partial content, so use getPage for complete pages. Nothing is left 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, covering the safety and side-effect profile. The description adds useful return-shape context (titles and direct links), but does not disclose result limits, pagination, or ranking 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?

Three tight sentences with the purpose front-loaded, followed by usage conditions and return format. No filler or repetition.

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 single-parameter search tool with rich annotations and no output schema, the definition is nearly complete. The remaining gap is query-formulation and result-set behavior, which an agent would need before relying on the results.

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 the single 'query' parameter, so the schema contributes nothing. The description implies natural-language/intent-based querying via the 'answer questions' framing, but never documents query syntax, length limits, or whether it supports keywords vs phrases.

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 verb (search) and resource (documentation) plus the content types it covers (code examples, API references, guides). It distinguishes itself reasonably from getPage by framing itself as cross-corpus retrieval, but never names the sibling explicitly.

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

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

Provides explicit when-to-use context ('answer questions about Sewlore Docs', 'find specific documentation', 'understand how features work', 'locate implementation details'). However, it gives no exclusion guidance versus getPage, so the boundary between search and direct page retrieval is left 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?

Annotations declare a non-read-only, non-destructive, non-idempotent, open-world write; the description fills in what that actually means — the report goes to a human documentation team, must be deduplicated per conversation, and must exclude confidential conversation content. What's missing is what the caller gets back (confirmation, ticket id) or any 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?

Purpose and trigger conditions are front-loaded, and each sentence adds a distinct rule (sanity check, unverified user reports, dedupe, exclusion). Slightly longer than needed — the 'no need to exhaustively re-read the page' aside could be folded into the sanity-check clause.

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 reporting tool with no output schema, the description covers what triggers it, how to scope a submission, and privacy constraints. Only the post-submission outcome is left unspecified, which is a minor gap given no output schema exists to describe it.

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

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

Schema description coverage is 100%, so goal, content, and pageUrl are already fully documented with length limits and examples. The description adds only a light constraint ('one call per distinct issue' implies one issue per content field) and no format details beyond the schema.

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

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

States a specific verb and resource ('Report an issue in the documentation of Sewlore Docs') plus the consequence ('so the team can fix it'). It is unmistakable against siblings getPage and searchDocumentation, which read versus report.

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

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

Explicitly enumerates when to use (outdated, contradictory, missing, unhelpful content; user-reported problems even if unverified) and when not to ('Do not use this tool to confirm that a page is accurate'). It also gives operational guidance — sanity check before reporting, one call per distinct issue, no duplicates in a conversation.

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