Read document content

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

With no annotations provided, the description must carry the burden of behavioral disclosure. It does explain that content is stored in a collaborative blob and can only be retrieved through this tool, which is a significant behavioral detail. However, it doesn't disclose the return format beyond markdown default, error conditions, or whether it's a read-only operation (though 'Fetch' implies it). The description adds valuable context but lacks completeness.

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 two sentences, concise and front-loaded with the core action ('Fetch a document title and its full content by ID'). The second sentence about the collaborative blob adds necessary context without fluff. Slightly verbose but efficient overall, earning a 4 rather than 5 due to minor redundancy.

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?

Given the tool's simplicity (2 params, no output schema), the description covers the essential: what it does, the default format, and the uniqueness of content retrieval. It lacks details on error handling, authentication, or performance, but for a read tool with clear purpose, it's adequately complete. No output schema means it doesn't need to explain return values, so the description is sufficient.

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 50%, with documentId having a basic description but format only having an enum. The description adds meaning for format by explaining markdown is default and content is markdown by default, but doesn't explain the difference between html and markup. It does not elaborate on documentId beyond schema, so it partially compensates for the coverage gap but not fully.

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 verb 'Fetch' and the resource 'document title and its full content by ID', which precisely defines the tool's purpose. It also distinguishes itself from siblings like huly_list_documents by noting it retrieves full content, not just metadata. The mention of markdown by default and the collaborative blob uniqueness sets it apart.

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 implies usage when you need the full content of a specific document, contrasting with list/search tools that provide summaries. However, it doesn't explicitly state when not to use it or mention alternatives like huly_get_issue, but the context signals with siblings provide enough guidance. The statement about the collaborative blob implies this is the only way to get content, but without explicit exclusions.

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