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

Goes well beyond the annotations: it discloses that the write REPLACES prior state and never appends (no history is kept), that reviews are owner-scoped and never leak across users, that the tool is tier-gated (sp500+), and that corrected_value on a non-corrected review is rejected. These are real behavioral constraints an agent could not infer from readOnlyHint/idempotentHint alone.

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 purpose and upsert semantics, then key-minting, then state values, then constraints — a sensible order. It is dense but somewhat long, and the state definitions duplicate the enum descriptions already present in the schema.

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 5-parameter mutation tool it covers everything an agent needs: key construction, update-vs-create semantics, state meanings, the conditional corrected_value rule, ownership scoping, and the tier gate. Return values need not be explained since an output schema exists.

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 is 3, but the description adds genuine meaning beyond the schema: the rationale for minting a per-figure key ('one fact can back two numbers in one sentence, and a key carrying only the fact_id makes one verdict cover both'), the lowercase/whitespace-collapsed convention with a worked example, and the state/corrected_value coupling. The state enum is largely restated from the schema, which keeps it from a 5.

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 ('Record (or update) the review state of ONE figure inside a report') and immediately frames the scope as a single figure, distinguishing it from report-level siblings like verify_report_figures or sign_off_report. The 'durable answer to has a human traced this number' framing makes the intent unambiguous.

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?

Clearly establishes when to call it (recording or updating a per-figure verdict) and the upsert rule that re-reviewing replaces rather than appends. It does not name alternatives (e.g. list_figure_reviews to inspect existing marks, verify_report_figures for bulk verification) or state when not to use it, so it falls short of explicit routing.

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