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

Annotations declare destructiveHint=true, openWorldHint=true, idempotentHint=false. The description adds valuable negative disclosures not in the annotations - it does not publish, does not copy credentials, does not prove runtime data safety - which tells the agent the blast radius is bounded to a recorded proposal, and it states the production baseline precondition.

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?

Three sentences, front-loaded with the core action, then preconditions, then explicit non-goals. Dense but every sentence earns its place; minor jargon cost does not justify penalizing structure.

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, non-idempotent, open-world mutation with no output schema and 7 undocumented parameters, the safety non-goals are a good start, but the description never explains the parameters, the expected response, or how 'record a proposal' relates to the later verify/reconcile/publish steps in the release lifecycle.

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?

Seven parameters with 0% schema description coverage, and the description names none of them. 'exact-commit', 'build/config/migration boundary', and 'same-environment baseline' only obliquely gesture at commit_sha, config_requirements, migration_ids, and environment; app_id, expected_revision, and previous_release_id are entirely unexplained.

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 compound action: 'inspect exact-commit source boundaries and record a code-only Git/Vercel proposal.' This distinguishes it from publishing/deploying siblings, though the jargon ('source boundaries', 'code-only proposal') makes the exact output object ambiguous for an agent unfamiliar with BEON's model.

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 real conditions: production requires an unchanged build/config/migration boundary against a verified same-environment baseline, and first releases need separate review. It does not name direct sibling alternatives (e.g. reconcile/verify), but the production-vs-first-release gating is concrete usage guidance.

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