List Deleted Punch Items

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

The description adds useful error behavior (401/403/404 status codes) and confirms it is read-only, which is already indicated by annotations. However, the contradictory return-type statements (array vs single object) create confusion about the response shape, reducing transparency.

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 contains redundant and contradictory sentences: 'Return an array' conflicts with 'Returns a single JSON object,' and 'Required parameters: project_id' merely repeats schema information. The API path and endpoint are useful, but the contradictory statements add noise and the structure could be much tighter.

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 simple list tool with one parameter, the description should clearly state whether it returns a list or a single object, and whether pagination applies. It fails to do so, presenting contradictory information and omitting any mention of pagination, ordering, or filtering. The lack of an output schema makes this ambiguity worse.

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 coverage is 100% for the single parameter, and the description merely restates that project_id is required without adding new meaning beyond what the schema already documents. It does not explain format, constraints, or how the parameter is used beyond 'specified Project.'

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 initially states it returns an array of Deleted Punch objects for a specified Project, but then immediately says it returns a single JSON object describing the deleted punch item. This internal contradiction obscures the tool's actual purpose. The name and endpoint suggest a list operation, yet the usage guidance implies a single-item lookup.

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 a usage hint ('Use this when you already know which deleted punch item you want'), but this is misleading because the tool only takes project_id and targets the recycle bin endpoint, implying it lists all deleted items rather than fetching a specific one. No alternatives are mentioned, and the guidance conflicts with the tool's list-like behavior.

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