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

With readOnlyHint, idempotentHint, and destructiveHint already provided by annotations, the description adds value by disclosing the response fields (title, description, archived, app_url) and the plan-gating nuance where users without timeline access land on the billing page. This goes beyond the annotations and helps the agent anticipate behavior when navigating from the returned app_url.

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 appropriately sized; it front-loads the core purpose in the first sentence and then adds useful contextual details about the returned fields, related views, and plan gating. While a bit dense, each sentence earns its place without extraneous fluff.

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 simple read operation with two parameters and no output schema, the description provides a solid picture of what to expect: the fields returned and a notable behavioral quirk (timeline gating). It doesn't cover error cases or exhaustive return format, but it is sufficient for a retrieval tool of this complexity.

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 schema already provides descriptions for both parameters: company_id as 'ID of the company that owns the projects' and pk as 'The id of the project'. With high schema coverage, the baseline is 3. The description adds no parameter-specific syntactic details, but none are needed beyond what the schema offers.

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 'Retrieve a single project by id within a company' — a specific verb, resource, and scope. It distinguishes from sibling list_projects (list many) and update/destroy/create by clearly being a read operation for one project. The title 'Get a project' aligns with the description.

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 when to use this tool: when you need a single project's details, including title, description, archived status, and app_url. It doesn't explicitly name alternatives like list_projects, but the distinction is clear from the 'single project' wording. It also provides context about the timeline being plan-gated, which helps avoid unexpected behavior. No explicit when-not-to-use, hence not a 5.

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