Ingest report

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses the report's scope (parse failures, ignored rows, degraded cases) and the important behavioral fact that it is empty on the shipped dataset, preventing a wasted call or a false-negative interpretation.

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?

A single front-loaded sentence that names the report, lists its contents, and closes with the most decision-relevant fact (empty on shipped data). No filler or restatement of the title.

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?

With no parameters, no output schema, and full annotation coverage, the description carries its share by enumerating what the report returns. A minor gap remains: it doesn't indicate the output format or explicitly position itself against ghost_review_queue, which covers the similarly-named needs_manual_review cases.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly implies a no-argument, no-filtering report rather than suggesting options that don't exist.

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?

The description names the specific resource (ingestion diagnostics) and enumerates exactly what the report contains: unparsed evidence files, ignored rows/log lines, CSV issues, and cases degraded to INCOMPLETE + needs_manual_review. That content list distinguishes it from generic siblings. It stops short of a clean verb framing ('returns/reads'), but the intent is 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?

The note 'Empty on the shipped dataset' is a genuine usage signal that tells an agent not to expect output in the common case. However, it does not state when to call this versus the overlapping siblings ghost_review_queue or ghost_verify_output, nor does it say whether to call it proactively or only after an ingest failure.

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