EvalGate Docs

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without description help. The description adds nothing beyond that, which is appropriate for a simple read, but it is silent on what happens with an unknown or malformed slug.

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?

One short, front-loaded sentence with no wasted wording. It is efficient, though the terseness contributes to the missing operational detail rather than being purely a virtue.

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 is simple, the annotations are rich, and there is no output schema to explain, so the description need not do much. However, for a lookup-by-key tool, the omission of slug semantics and the absence of any pointer to the sibling discovery tools leaves a real operational 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?

The single parameter 'slug' has 0% schema description coverage, so the burden is entirely on the description, which never explains what a slug is, its format, or how to obtain one (presumably from docs_list or docs_search). This is the clearest gap in the definition.

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 ('Read') and a specific resource ('one page from the published EvalGate documentation index'), which is clearly distinct from listing or searching. It does not explicitly name the sibling tools it differs from, but 'one page' implies a single-item fetch, which differentiates it adequately.

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: an agent infers this is the tool to call once it already has a page identifier, and that docs_list/docs_search are the discovery path. No explicit when-to-use or when-not-to-use statement, and no prerequisite about knowing the slug upfront.

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 bar is low; the description adds real behavior beyond them by disclosing that only published pages are returned and that omitting both params yields the complete catalog rather than a 25-item page. It does not say how results are ordered or what a page entry contains.

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 padding, with the resource scope front-loaded and the pagination instruction following immediately. Every clause carries information an agent needs.

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 two-parameter, zero-required read tool with full schema coverage and rich annotations, the description covers scope, pagination and the unpaginated case. The only real omission is routing guidance relative to docs_search and docs_get.

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 both parameters are already documented, and the description adds mainly the interaction case: omitting limit and cursor together returns everything, resolving the schema's ambiguous 'defaults to 25 when paginating'. That is a modest value-add over the schema, fitting the baseline of 3.

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 published EvalGate documentation pages') plus a filter ('published'), which cleanly separates it from docs_get and docs_search by implication. It stops short of explicitly naming those siblings, 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?

Gives concrete invocation guidance for pagination ('omit both to list the complete catalog'), which is genuine when-to-do-what direction. However, it never states when to reach for docs_search or docs_get instead, leaving the sibling 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile needs no restating. The description adds genuine scope information — only reviewed/published documentation is indexed, so drafts and unreviewed pages will not appear — but says nothing about match semantics, ranking, truncation, or how the limit is applied.

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 no filler or redundancy, which is well structured. Its brevity is efficient rather than padded, though the same one sentence could have absorbed a clause on matching or sibling routing without becoming bloated.

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 two-parameter search tool with no output schema, the description omits everything an agent needs beyond the verb: result shape, ranking or relevance behavior, empty-result handling, and how it relates to the two sibling documentation tools. The annotations cover safety but not the search semantics.

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, so the description carries the full burden and adds essentially nothing: it does not explain whether 'query' is keyword, phrase, or full-text, how matching works, what a limit of 10 actually bounds, or what happens with zero hits.

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 ('Search') and a specific resource ('the reviewed index of published EvalGate documentation'), and the qualifier 'reviewed/published' scopes exactly which content is searchable. It does not, however, explicitly distinguish itself from docs_get or docs_list beyond the implicit search-vs-get-vs-list contrast.

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 statement about when to use this tool versus docs_get or docs_list, and no exclusions or prerequisites. An agent must infer the split from the sibling names alone, which is thin guidance for three overlapping documentation tools.

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