SiteGPT Docs

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

Beyond the annotations, the description discloses many behavioral traits: the filesystem is a virtual sandbox, not a real shell; calls are stateless and reset to `/`; output is truncated to 30KB; nonexistent paths mean a wrong guess rather than an undocumented topic; and paths map from URL to `.mdx`. This gives the agent a strong mental model of how the tool behaves.

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 long but well-organized with bold section headers, examples, and front-loaded purpose. Some redundancy exists, such as mentioning no network/writes early and again in the supported-commands section, so not every sentence is strictly essential. However, the density of practical detail is largely justified for a shell-like tool.

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 shell emulator with no output schema, the description is remarkably complete: it covers command semantics, path discovery, error interpretation, statelessness, output truncation, OpenAPI usage, and how to present paths as URLs to the user. Nothing critical is missing for an agent to invoke it 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?

Although the schema already documents the single `command` parameter at 100% coverage, the description adds substantial meaning: supported commands, command chaining with `&&`, absolute paths, path-to-URL conversion, OpenAPI mount points, and concrete examples for rg, tree, head, cat, and jq. This goes well beyond the baseline schema description.

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 opens with a specific verb and resource: "Run a read-only shell-like query against a virtualized, in-memory filesystem" containing SiteGPT Docs pages and OpenAPI specs. It also differentiates itself from the search tool by explaining that page reading, structural exploration, and exact keyword/regex matching happen here, not in a separate get-page 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?

The workflow section explicitly says to start with the search tool for broad or conceptual queries and to use this tool for exact keyword/regex matching, structural exploration, or reading a full page by path. It also contrasts with search_site_gpt_docs and provides clear exclusions such as no writes, no network, and no process control.

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 safety (readOnlyHint, idempotentHint, non-destructive). The description adds meaningful behavioral context beyond annotations by disclosing that the result is contextual content with titles and links, that it does not return full page text, and that .mdx must be appended for filesystem reads. This is exactly the kind of extra context an agent needs.

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 three sentences with no filler: purpose is front-loaded, usage guidance follows, and the alternative tool/routing detail is at the end. Every sentence earns its place, and the concrete example with head -200 is especially clear.

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 search tool with two simple parameters and no output schema, the description covers everything needed: when to call it, what it returns, and how to get full content from the sibling tool. There are no significant gaps in context for correct selection and 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 100%, so the schema already documents both parameters ('query' and 'version'). The description does not add parameter-specific semantics, but it also doesn't need to, given full schema coverage. Baseline 3 is appropriate here.

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 explicitly states a specific action ('Search across the SiteGPT Docs knowledge base') and a concrete resource, listing what kinds of content are retrieved (code examples, API references, guides). It also differentiates itself from the sibling tool by clarifying search returns titles/links and directing full-page reads to query_docs_filesystem.

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 explicit when-to-use guidance ('Use this tool when you need to answer questions...') and also an explicit when-not-to-use alternative: if full page content is needed, use query_docs_filesystem with the .mdx path. This is model behavior for routing an agent to the correct sibling.

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 convey that this is a write operation (readOnlyHint=false, idempotentHint=false), and the description adds meaningful context: feedback is routed to the docs team and is scoped to documentation content. It stops short of describing what happens after submission (e.g., whether a confirmation is returned, whether it creates an issue), but it does not contradict the annotations and provides useful behavioral framing.

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 sentences, all informative. The first sentence states the purpose, the second gives concrete usage criteria, and the third excludes non-documentation feedback. No filler or redundancy; the most important information is front-loaded.

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 two-parameter tool with no output schema, the description and schema together cover the essential information: what to submit, which page, what kind of feedback, and when to use it. The only minor gap is the lack of detail about the post-submission result or confirmation behavior, which is not critical but would make it 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 100%, and the parameter descriptions already explain 'path' (URL path without .mdx extension) and 'feedback' (clear description of the issue). The tool description reinforces the kind of feedback expected but adds no technical semantics beyond the schema, so the baseline score of 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?

The description clearly states the tool's function: 'Report a problem with this documentation site so the docs team can fix it.' It identifies the specific resource (documentation site) and the action (reporting a problem), and it distinguishes itself from the sibling query/search tools by being feedback-oriented. It also explicitly carves out what it is not for: product support or feedback about the tool/assistant.

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 explicit when-to-use guidance: 'Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example.' It also provides a clear when-not-to-use boundary: 'not for product support requests or feedback about this tool or assistant.' This is strong, actionable usage direction.

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