aethis_review_project

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

Annotations already cover read-only, non-destructive, open-world, and non-idempotent. The description adds real behavioral context beyond them: it is advisory-only, the deterministic path needs no LLM key, and coach=true requires a configured Anthropic key. It does not explain why the read is non-idempotent (the LLM narrative can vary), a minor omission.

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 purpose and return shape before the advisory/key caveats; no filler. Slightly dense but every sentence carries information an agent needs.

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 output schema, the description carries the return-value burden and does so: it enumerates score, per-check evidence dimensions, strengths, and the next improvement. Combined with the advisory-only note and key requirements, an agent has everything needed to call it correctly.

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% and the schema itself documents every parameter in detail, including the key-resolution chain and the retired openai_key. The description only restates the coach/key relationship, adding framing but no semantics 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?

States a specific verb (review) and resource (authoring project) plus the rubric it applies, and describes the distinctive output (score, per-check evidence across grounding/process/lifecycle, strengths, next improvement). This separates it cleanly from the sibling validate/refine/explain tools, which do not produce skill-building feedback.

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?

Tells the agent this is advisory and 'never blocks publishing', which contrasts usefully with the gating validate_* siblings, and explains the condition for opting into coach=true. It stops short of an explicit 'use this instead of X when Y' routing statement, so it is clear context rather than full when/when-not guidance.

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