SMSPVA Documentation

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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description usefully adds that examples are verbatim, not run, not translated, and do not make live requests. It also discloses return shape hints like available_languages, source lines, and pagination.

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 four compact sentences and front-loads the core purpose. Every sentence adds useful information about filtering, return values, or non-behavior.

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 helpfully names returned fields such as available_languages, source lines, and pagination. The schema supplies page and locale details, though limit/offset behavior could be clearer.

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 50%: page, locale, and language have schema descriptions, while kind, limit, and offset do not. The description clarifies the language/kind filters and pagination, but does not explain limit/offset semantics beyond the schema's numeric bounds.

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: get verbatim fenced examples from a page, with language/kind filtering and no execution. It is clearly distinct in substance from read/list/search siblings, but it does not explicitly name or contrast those alternatives.

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

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

The intended use is implied by 'examples from a page' and the filterable language/kind fields. However, there is no explicit when-to-use guidance or comparison against smspva_docs_read_page, search, or list_pages.

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 cover safe-read, idempotency and closed-world behavior, so credit here is for added context: the description discloses exactly which fields come back and names the pagination cursor (next_offset), which matters because there is no output schema. It omits termination behavior and any default page size, keeping it short of a 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?

Two sentences, front-loaded with the resource and returned fields, with the pagination hint placed last where it belongs. Minor friction: it refers to 'next_offset', a field name that appears nowhere in the input schema, which could momentarily confuse an agent looking at the offset parameter.

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 four-parameter read-only listing tool with no output schema, the definition covers what is returned, how to filter, and how to page through results. Remaining gaps (ordering, total counts, page-size defaults) are modest and partly handled by the limit/offset schema bounds.

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 50%: locale and section are documented in the schema, while limit and offset are not. The description partially compensates by tying 'optionally filtered by API family' to section and framing offset as a cursor follow-up, but limit's default and maximum behavior is left undocumented in both places.

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 (list documentation pages) and even names the returned fields (IDs, titles, descriptions) plus the language scoping. It is distinguishable from smspva_docs_read_page and smspva_docs_search by being the enumeration path, though it never explicitly contrasts itself with those siblings.

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?

Implies usage through 'optionally filtered by API family' and gives a pagination instruction ('Follow next_offset to browse all pages'), which is a real operational hint. However, it never says when to prefer this over smspva_docs_search or smspva_docs_read_page, leaving the routing decision 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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description earns credit by adding pagination termination semantics, Unicode code-point counting for offsets, and an explicit confirmation that no external URL or filesystem access is possible — behavior not derivable from 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?

Three tight sentences with the core action first, then pagination mechanics, then the access boundary. Every clause carries information; nothing is restated from the title or annotations.

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 read-only paginated fetch with no output schema, the description covers how to page, how offsets are measured, and what access is unavailable. Only the return envelope shape (e.g. presence of the next_offset field itself) is left implicit.

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 only 50%, with offset and max_chars carrying no in-schema description; the description compensates by explaining that offsets and max_chars are measured in Unicode code points. It stops short of stating defaults or that next_offset is a return-field sentinel, so page/locale details lean on 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 ('Read Markdown for a page') plus the locale scoping, which is more precise than the title alone. It does not explicitly differentiate itself from siblings like smspva_docs_search or smspva_docs_get_examples, though 'page' vs 'examples'/'list' implies the distinction.

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 concrete in-tool guidance ('Follow next_offset until null') and a boundary ('No filesystem or external URL access'), but it never says when to reach for this tool versus search or list_pages. The retrieval workflow is only implied by the schema note that page IDs come 'from search/list'.

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 and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: lexical matching with accent handling, title prioritization, deduplication of repeated code boilerplate, and the exact return shape (page IDs, snippets, relative 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 dense sentences with zero filler, and the core purpose plus the read_page handoff are front-loaded before the lower-value return-shape detail.

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 usefully states what comes back, and the annotations cover safety. The only material gaps are the undocumented limit parameter and any indication of ranking or result-volume 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 coverage is 50%: locale and section are documented in-schema, but query and limit are not. The description compensates partly by clarifying that query is lexical and accent-tolerant and that results are confined to one language, but it says nothing about the limit parameter or section filtering. 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 guides, API methods and warnings') and adds search characteristics (lexical, accent-aware, title-boosted). It routes the agent to read_page for full context, distinguishing it from that sibling, though it does not differentiate itself from list_pages or get_examples.

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?

'use read_page for complete context' gives an explicit handwritten alternative and the condition for it. It does not say when to prefer list_pages or get_examples, and the single-language constraint lives only in the schema.

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