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

Goes well beyond the annotations (which only say readOnlyHint=false, destructiveHint=false): it discloses immediate re-evaluation of existing applicants, that refreshedCount reports how many suggestions changed, and that already-APPROVED reviews are never touched — a key safety boundary for an agent. It also flags the unusual replace-vs-patch semantics for conditions and actionSuggestedLabelIds.

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?

Dense but zero-waste: purpose and the partial-update/replace distinction are front-loaded, then the condition grammar, then the side-effect on existing applicants. Every clause carries information the agent would otherwise have to guess.

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 6-parameter mutation tool with no output schema and a nested conditions structure that the schema leaves undefined, the description covers purpose, payload shape, replacement semantics, return signal (refreshedCount), and the APPROVED-review exclusion. Nothing an agent needs to invoke 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds substantial meaning the schema lacks: the conditions array has no item schema at all, and the description supplies its full grammar (type, operator, questionId, value), per-type constraints (questionId required for question, contains unsupported for emailDomain), operator-specific value rules (exists takes none; gt/lt are numeric and question-only), and the AND semantics across conditions.

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+resource ("Update an auto-review rule") scoped to "this beta project's applicant screening", which cleanly separates it from createApplicantRule and deleteApplicantRule in the sibling list without needing the 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 clear operative guidance: supply only the fields to change, and names getScreeningSetup as the source of questionId. It does not explicitly route the agent to createApplicantRule for new rules or deleteApplicantRule for removal, so the alternative-selection guidance is contextual rather than explicit.

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