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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the description's job is to add the non-obvious constraints — which it does: it discloses a privacy rule (no personal data or result values) and a content requirement (describe what you called). It does not say what happens after submission (confirmation, ticket id, rate limiting), leaving a small gap.

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 sentences, front-loaded with the action and recipient before the conditional usage rules, with no filler. Dense but readable; minor overlap between the enumerated problem types and the later 'problems you could not work around' clause.

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 simple 3-parameter, non-destructive reporting tool with no output schema, the description covers what to do, when to do it, what to include, and what not to include. Only the post-submission behavior is unstated, which is a small omission given there is no output schema to rely on.

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 67% and the category enum has no schema description, so the description compensates by enumerating the problem classes in the same order as the enum values (wrong type, missing data, confusing error, wrong result), letting an agent map its situation to a category. The 'describe what you called and what went wrong' phrasing adds intent beyond the message field's own min/max-length description; dataset_id is left to 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 and recipient ('Tell the datatomcp team') plus the exact class of defect (wrong column type, missing values, unactionable error, wrong result). It is unmistakably distinct from the query-oriented siblings (query_rows, describe_dataset, aggregate) because it produces feedback to the maintainers rather than data.

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 explicit both-sides guidance: use it rarely, only for problems you could not work around, and never for ordinary questions or empty results. The exclusion of empty results is exactly the ambiguity an agent would otherwise get wrong, since empty results are a common false-positive trigger for issue reporting.

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