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

The description discloses key behavior: the document is immutable ('first immutable'), and 'reviewed' is metadata not approval. It also implies idempotent creation via 'first' and hints at non-destructive nature. However, it doesn't detail error conditions or whether creation overwrites, but annotations (idempotentHint true, destructiveHint false) complement this reasonably well.

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 concise (two sentences) and well-structured, front-loading the primary purpose and then adding context about optional parameters and semantics. No verbosity or 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?

For a create operation with a detailed input schema, the description covers essential context: the immutable nature, the document types, the optional ticket_id scope, and the meaning of reviewed. It doesn't mention output behavior (since there's an output schema), but the absence of output details is acceptable per rubric guidance. It could be slightly more complete on parameter semantics but is adequate.

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 description explains ticket_id (scopes to linked feature) and status/reviewed (editorial metadata). Other parameters like request_id, project_id, title, body, and kind are not individually described, but their meaning is largely inferable from names and schema constraints (e.g., title maxLength, kind enum). This partially compensates for the 0% schema description coverage.

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 purpose: saving an immutable project document (brief, PRD, tech spec, or decision revision). It uses specific verbs ('Save') and identifies the resource ('immutable project brief, PRD, technical specification or decision revision'), distinguishing it from other document tools like project_document_get and project_document_revise.

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 provides usage context by explaining optional ticket_id scoping and clarifying that 'reviewed' is editorial metadata, not execution approval. However, it does not explicitly state when to use this tool versus alternatives like project_document_revise or project_document_get, leaving some inference to the agent.

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