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

Beyond the annotations (destructiveHint=true, idempotentHint=true, openWorldHint=true), it discloses the downstream consequence that approval feeds payroll and may not be undoable via the API. That is exactly the kind of context annotations cannot convey. It is consistent with destructiveHint=true rather than contradicting it.

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?

Two sentences, front-loaded with the WRITE marker and the verb, zero filler. The irreversibility warning is placed before the guardrail clause, so the highest-risk information lands first.

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 destructive one-parameter mutation with no output schema, the description covers the essential risk profile and the exact-call guardrail. The notable gap is preconditions: it never says whether the time card must be in a pending/unapproved state, which matters for an agent choosing when to call.

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 one parameter at 100% schema coverage, the schema already documents time_card_id fully, and the description only reinforces that a single specific card is targeted. No additional semantics (valid ranges, statuses, how to obtain the id) are added, so the baseline 3 applies.

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 (approve), a single resource (ONE time card), and even the underlying endpoint (PATCH .../time_cards/{id}/approve). The emphasis on ONE cleanly separates it from the list/get siblings, which read time cards rather than mutate them.

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 gating condition: only call it when the user asked to approve this exact time card, which rules out speculative or batch usage. It does not name an alternative path (e.g., use workyard_get_time_card first to confirm status), so it falls short of full when/when-not/alternatives guidance.

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