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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses one hard gate — no credit below 0.90 retention — but says nothing about what a failed call returns (error vs. no-op), whether issuance is idempotent, what 'agent' identifies, or what side effect the credit produces. For an unannotated mutation tool that is a substantial gap.

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?

A single compact sentence with the purpose front-loaded and the constraint immediately following. Nothing is padded, though the telegraphic register costs some clarity.

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 an unannotated, mutating tool with no output schema and 0% schema coverage, the definition should explain failure behavior and the 'agent' input. Only the threshold condition is covered, so an agent could still call this correctly in the happy path but not reason about rejections or identity.

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 description coverage is 0%, so the description must compensate for both parameters. It does add real meaning to audit_retention by pinning the threshold at 0.90, but the required 'agent' parameter is entirely undefined — ID vs. name, format, or whether it must exist beforehand is left open.

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 names the resource ('Rest-credit issuance') and its gating condition, which is enough to tell it is a credit-granting operation rather than a status read like duty_state. But it opens with a noun phrase instead of a verb, and it never contrasts itself with siblings such as duty_record_event or duty_check, so an agent must infer that this is the mutation that grants rest credit.

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 parenthetical gives a precondition (audit_retention >= 0.90) but never states when to call this versus duty_record_event or duty_check, nor what to do when the audit fails. A precondition is not the same as usage routing, so the agent is left to infer the workflow.

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