Retrieve Recycled Injury

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

Annotations already provide some behavioral hints (non-read-only, non-destructive, non-idempotent). The description adds that it 'returns the modified object' and mentions the endpoint, but the contradictory language ('retrieves' vs 'updates') undermines clarity. The tool's true behavior (restore from recycle bin) is not clearly stated.

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 only three sentences but is repetitive and confusing. It mixes retrieval and update terminology, wasting words. A clearer, more focused description would be more concise.

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 large number of sibling injury tools, the description should uniquely identify this tool as a restore operation. Instead, it confuses by implying retrieval. It does not specify what is returned (only 'modified object') and lacks output schema. The restore action is not explicitly named.

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%, so each parameter has a description. The description redundantly lists required parameters but adds no new meaning beyond the schema. The incident_id parameter is not explained in the description, but the schema covers it.

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 is contradictory: it starts by saying 'Retrieves a specific Injury' but then says 'Use this to update an existing Incidents' and 'Updates the specified Incidents'. The endpoint is a PATCH restore, so the tool is not a retrieval but a restoration. This inconsistency makes the purpose unclear.

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?

No explicit guidance on when to use vs alternatives. The description mentions 'use this to update an existing Incidents' but does not clarify context or when not to use. With many sibling injury tools (e.g., update_injury, restore...), the lack of usage guidance is a gap.

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