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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description reinforces this with irreversibility language and the GraphQL mutation name. It also discloses the return value ('Returns true when deleted'), which matters because there is no output schema. It does not cover failure modes (e.g., deleting an approved/locked entry) or permission requirements.

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?

Front-loads the risk classification ('WRITE, DESTRUCTIVE'), then the action, the id source, the irreversibility, and the return value in four short clauses. No sentence is filler.

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 one-parameter destructive call with no output schema, it covers action, id provenance, irreversibility, and return value. Missing only edge-case behavior such as what happens if the id is unknown or the entry is already approved, which would help an agent recover from errors.

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% with a single required entry_id, so the schema already defines type and constraints. The description adds meaning beyond the schema by stating how to obtain a valid id, which the schema does not say.

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?

States a specific verb and resource ('permanently delete one timesheet entry by id'), scoped to a single entry so it is clearly distinct from list/update siblings. It even names the sibling to use for retrieving the id, so an agent can route without opening a schema.

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?

Gives an explicit prerequisite workflow ('get it from kiwihr_get_timesheet') and an explicit hazard ('This cannot be undone'). It does not explicitly contrast with kiwihr_update_timesheet_entry for the case where the user actually wants to amend rather than remove, which is the one remaining inference left to the agent.

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