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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: no AI model runs, the call itself never consumes allowance, the allowance is per-account so rotating keys doesn't reset it, fair-use caps of 20 per project and 60 per account per month, plus 8 MB and 120 calls/minute (5,000/day) limits. These are exactly the operational constraints an agent cannot get from structured fields.

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-loaded with the answer (used, left, reset date, what to do at the limit) before the accounting rules. It is dense and long for a no-argument status call, and the fair-use paragraph and the project-identity rules could be tightened, but each sentence conveys non-obvious quota semantics rather than 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 zero-param read tool with an output schema, the description names the response shape (shoot-plan.allowance/1 with projects_used, projects_allowed, projects_left, resets_on, message) and covers auth (agent key from a Shoot Plan account), cost (no AI model runs, never counts), and throughput limits. Nothing an agent needs to call it correctly is missing.

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?

Zero parameters, so there is nothing to disambiguate; the description explicitly says "Input: none," confirming the empty schema. Baseline 4 applies with no parameter semantics to add.

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: reports used/remaining monthly project allowance, reset date, and remedies when exhausted. It also defines precisely what counts as a "project" (plan work id + title) and which calls consume allowance, so the agent knows exactly what the number means. No sibling tool covers quotas, so the differentiation burden is low.

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?

"Call this before starting a project if you want to know whether a finished document will be available" gives an explicit trigger condition, and the counting rules implicitly tell the agent when it is unnecessary (drafting, checking, fixing never count). What's missing is a named fallback/alternative when the limit is reached, which the description only gestures at with "how to carry on sooner."

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