AGILEX Docs

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

With no annotations supplied, the description carries the full burden and does so well: it discloses page sizes (20k-60k chars), the pagination contract (truncated/next_offset/offset), and the complete response field list including url for citation. The main failure mode an agent would hit — looping or truncating content — is pre-empted.

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

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

Front-loaded with purpose, then pagination protocol, then args — good ordering with no filler. The Args block partially restates schema defaults, which is mildly redundant, and the Returns section repeats schema-derivable field names, but both stay short.

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 tool with an output schema, this covers everything an agent needs: input provenance, paging loop, size limits, and citation instruction. Nothing required to invoke it correctly is missing.

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

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

Schema description coverage is 0%, yet the description documents all three parameters with meaning beyond types: doc_id accepts a search_docs id or a page slug, max_chars carries default 20000 and max 120000, offset is the start position defaulting to 0. That fully compensates for the schema 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?

Opens with a specific verb and resource ('Read one documentation page as Markdown'), which immediately separates it from list_docs/list_spaces (enumeration) and search_docs (discovery). The 'one page' scoping and the doc_id provenance make it unambiguous which sibling produces the input for this 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?

Gives a clear entry condition: call this with a doc_id returned by search_docs, and explains the pagination continuation loop with an explicit anti-pattern ('do not re-request the same offset'). It does not state when NOT to use it (e.g., browse via list_docs instead), so it stops short of full alternative routing.

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 pagination via offset, limit range and default, and the return JSON shape, but it does not state permission/access scope, ordering, rate limits, or whether all accessible spaces are searched when 'space' is omitted.

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 short, front-loaded, and well-structured with Args and Returns sections. The return-shape line is somewhat redundant because an output schema already exists, but the parameter documentation is efficient and earns its space.

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 three-parameter listing tool with an output schema and no annotations, the description provides the key usage context, all parameter meanings, and pagination behavior. Minor omissions remain around access scope and result ordering, but nothing critical to invoking it correctly is missing.

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

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

Schema description coverage is 0%, so the description must compensate, and it documents all three parameters with useful meaning: space accepts a slug or name fragment, limit is constrained to 1-300 with default 100, and offset supports pagination. The offset explanation is minimal, but the definition fills the main schema 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 gives a specific verb and resource: 'List documented pages, optionally inside one space.' It also distinguishes the inventory-style use case from answer-seeking search with 'rather than an answer,' which separates it from search_docs and get_doc without requiring the sibling schemas to be opened.

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 clearly states when to use it: when the caller wants an inventory of manuals rather than an answer. It implies the alternative search behavior, but it does not explicitly name search_docs or give other exclusions, so it falls short of fully explicit alternative routing.

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 disclosure burden. It establishes the 'public' scope and that this is a read/enumeration operation with no side effects, but says nothing about authorization requirements, whether the space list is complete or filtered per caller, or ordering/pagination of results.

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 blocks: purpose first, usage condition second, return payload third. Every sentence carries information and nothing is repeated from the schema.

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

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

For a nullary discovery tool with an output schema present, the description supplies the purpose, the selection condition, and an inline sketch of the return shape, which is sufficient to invoke it correctly. It stops short of explaining whether the space list is caller-scoped or what the 'chars' field measures.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The description correctly signals that enumeration is unfiltered and that the caller must do any narrowing downstream.

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 the public documentation spaces') plus a qualifier ('with page counts'), which is enough for an agent to distinguish it from the doc-level siblings get_doc, list_docs and search_docs. It never names those siblings explicitly, so the differentiation is implied by resource granularity rather than stated.

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 a concrete trigger: use it when the caller is unsure which product family a document belongs to, or to explain coverage. That is a real disambiguation rule against the search/list-docs siblings. It lacks an explicit when-not or a statement that this is the entry point for discovering space identifiers.

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 disclosure burden and does well: it describes the returned JSON shape and the practical link from doc_id to get_doc. It omits permission/auth requirements, rate limits, and behavior on zero results, which are the remaining gaps for a tool with zero annotation coverage.

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

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

The primary purpose and usage instruction are front-loaded, and the Args block is scannable. It is somewhat verbose, restating defaults already implied by the schema, but no sentence is genuinely wasted.

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

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

For a three-parameter read-only search tool with an existing output schema, nothing essential is missing: it covers when to use it, how to build a query, and how to chain into get_doc. Complexity is low and the description matches 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 coverage is 0%, so the description must compensate, and it does: query explains language support plus the exact product-name vocabulary with an example query, limit specifies the 1-25 range and default 8, and space gives concrete slug and Chinese-name examples.

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 ('Full-text search over the official AGILEX product documentation') and enumerates the content domains it covers (pinouts, CAN protocol, firmware, error codes). It is clearly distinguishable from siblings like get_doc/list_docs because it is the entry point search 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?

'Use this first for any question about AGILEX hardware' gives explicit priority ordering versus siblings, and the note that 'doc_id is what get_doc expects' names the natural follow-up tool. The trigger conditions are concrete and leave little to inference.

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