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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is not required to restate it. It adds genuinely non-obvious behavior instead: input is truncated at 20,000 characters and flagged, and unmatched statistic text is logged anonymously (date and text only) — a privacy-relevant side effect an agent should know about. No auth or rate-limit context, but the disclosure goes meaningfully beyond the annotations.

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 imperative 'Paste a whole draft', and the three sentences each carry distinct payload (input, processing/return shape, side effect). The middle sentence is dense with a long enumeration of return fields, but nothing is redundant.

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?

There is no output schema, so the description carries the return-value burden and does so fully: one row per statement with numbers found, match level, verdict, safe rephrasing, claim URL, or not_in_database status, plus counts by status and verdict. Combined with the truncation and logging disclosures, an agent has everything needed to call and interpret it.

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 description coverage is 100%, so both parameters (text and max_statements) are already documented in the schema, including the 20,000-character truncation rule. The description echoes the character limit and return shape but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

Specific verb+resource with explicit scope: it verifies an entire pasted draft rather than a single stat, which cleanly separates it from the sibling check_stat. The description states the pipeline (split into sentences, keep numeric ones, match against checked claims) so an agent can tell exactly what it does before opening 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?

Clear usage context is given: 'Paste a whole draft (a blog post, deck notes, an email, a social caption)' signals this is the bulk/whole-document entry point versus single-stat tools. It does not, however, explicitly name check_stat or state when NOT to use this tool (e.g., for a single claim), so the routing is implied rather than spelled out.

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