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

Annotations indicate readOnlyHint=false and destructiveHint=false, so the description must disclose mutation behavior. It does so by stating 'Change' and adds the valuable partial-update trait ('Only the fields you pass are touched'), which goes beyond what annotations provide. It does not mention error handling or idempotency, but given the annotation coverage, this is a solid disclosure.

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 a single, concise sentence that front-loads the core action. It avoids fluff and gets to the point quickly. The only issue is the erroneous 'lead' and slight inaccuracy in the field list, but the structure is efficient.

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 mutation tool with no output schema and 8 parameters, the description covers the partial-update behavior but omits several fields and includes an incorrect one. It does not address error scenarios, required parameter (project), or response format, but for a simple update tool, it is minimally sufficient. The gaps and the error reduce its completeness.

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?

With 63% schema description coverage, the schema already explains health, status, project, startDate, and targetDate. The description lists some fields but adds no new meaning and even introduces a non-existent 'lead' parameter. It omits description and startDate entirely, so it does not compensate for the undocumented parameters (name, summary, description). This is a net-negative contribution to parameter understanding.

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 with a specific verb ('Change') and resource ('a project'). It lists several updatable fields, which helps distinguish it from create/archive/delete siblings. However, it mentions 'lead' which is not a parameter, and omits 'description' and 'startDate', making it slightly inaccurate yet still conveying the core update intent.

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 phrase 'Only the fields you pass are touched' provides a key usage guideline about partial updates, implying you don't need to pass all fields. However, it does not explicitly contrast with sibling tools like create_project or archive_project, nor state when to prefer this tool over alternatives. The guidance is implicit rather than explicit.

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