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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds that it returns 'documented checks and correction steps' for a single named problem, which is useful framing, but it does not describe output depth, lookup behavior for unknown issues, or failure modes.

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 tight sentences with the general behavior front-loaded and the valid issue values grouped by document. Zero filler.

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?

An output schema exists, so return structure need not be explained, and the annotations cover the safety profile. The only remaining need is the when-to-use routing versus sibling tools, which is absent.

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 0%, and the flat enum lists do not document the cross-parameter constraint. The description compensates by mapping issues to documents (receipt_allocation, corrected_retry, return_mismatch on Statement 3; duplicate_document, gstr2b_mismatch, reversals on Annexure B; json_generation on both), which is real semantic value beyond the schema.

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 ('Returns the documented checks and correction steps') plus the resource (a known problem with a Statement 3 or Annexure B file) and scope ('one known problem'). This clearly separates it from siblings like validate_statement3 and generate_annexure_b, which act on files rather than explaining issues.

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?

Usage is implied (call it when you already know which issue you are dealing with, to get checks and correction steps), but the description never says when to prefer this over get_statement3_requirements or validate_statement3. No explicit exclusions or alternatives are given.

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