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

Annotations already declare readOnly=false, idempotent=true, destructive=false. The description adds non-obvious behavior: adoption freezes prior fields and section targets, locations are zero-based spans of persisted text, checks are bounded (checks_complete does not assess inherited analysis questions or qualification readiness), and no human approval is conferred.

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-loads the action and resource, then layers constraints and routing in compact sentences. Dense but every clause carries operational meaning; slightly run-on but not padded.

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 mutation tool with no output schema, 40% schema coverage and deep nesting, the description covers adoption/idempotency/routing well but says nothing about what is returned or the revision payload's meaning, and several nested fields remain undocumented.

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 only 40% across 5 required, nested parameters. The description usefully explains expectedReportRevision (echo from helvabase_draft_checks, null initially) and the span semantics, but leaves the `revision` object and the fields/key structure to the schema, so it only partly compensates for the coverage gap.

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 ('persist checks') against a specific resource ('the exact current draft and explicit text spans') and enumerates the three check kinds (support gaps, repeated commercial values, validity dates). It implicitly separates itself from the read-side sibling by pointing to helvabase_draft_checks, though it never says so directly.

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?

Explicit routing: 'Read the existing report with helvabase_draft_checks; do not rerun this mutation to diagnose a final-review refusal.' It also states the when-not condition for replays after adoption and that a changed draft needs a fresh clear report before final review/export.

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