Act on a project

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

Annotations already carry readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the description need only add nuance. It does by noting that amend requires a project that already has bids and that close stops accepting bids while reopen resumes—meaningful behavioral context. It doesn't detail all edge cases, but it is consistent with the annotations.

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?

One sentence encapsulates all four actions plus their role and prerequisites, with the most important categorical information ('Employer-side lifecycle actions') front-loaded. There is no filler or repetition of schema fields.

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?

The description provides the core semantics but omits state-transition constraints (e.g., whether close is final or whether reopen only applies after close) and any response/error behavior. Given no output schema and a destructiveHint=true, a bit more context about reversibility and required project state would make it more robust.

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 documents text and expired_at but leaves action values to the enum. The description maps each action enum value to the required parameter ('amend' implies text, 'extend' implies expired_at) and explains their purpose, which helps the agent select arguments. It doesn't waste space on project_id, which is self-explanatory, and with 50% schema coverage it sufficiently compensates.

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?

Description opens with 'Employer-side lifecycle actions' and then defines each of the four enum values with a concrete effect: 'amend adds an update...', 'extend moves the expiry date', 'close stops accepting bids', 'reopen resumes'. This gives an agent a specific verb, resource, and scope that distinguishes it from sibling tools like bid_action or update_project.

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 'Employer-side' qualifier signals that this tool is for the project owner, not freelancers, and the action-by-action breakdown clarifies when each variant is appropriate. However, it never names a sibling alternative or states a when-not-to-use condition, so an agent must infer the boundary from the sibling list.

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