aethis_discover_fields

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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false; the description usefully confirms the iteration model ('call repeatedly ... to improve completeness'), which matches the non-idempotent hint. However, it never discloses that the tool invokes an LLM and may require an Anthropic key or incur cost — that requirement is buried in the schema's key parameters rather than surfaced behaviorally.

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 front-loaded sentences: purpose, return payload, then workflow sequencing. Nothing is wasted, though the return-value sentence could arguably be dropped given how terse the rest is.

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?

No output schema exists, and the description compensates by naming the returned artifacts (names, types, descriptions, completeness) plus the recommended call sequence. It is largely complete for an extraction tool, with the only real gap being the unstated LLM/key dependency.

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 all five parameters (including the retired openai_key and the three auth-key variants) are documented in structured data. The description only implies that project_id selects the source-text scope and adds no syntax or format detail beyond the schema — 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+resource ('Discover input fields from the project's source text') and enumerates the outputs (field names, types, descriptions, completeness). It clearly differentiates itself from the sibling refine_fields, but stays silent on how it differs from validate_fields or set_field_spec, which also touch fields.

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 an explicit sequencing rule ('Run this BEFORE writing test cases') and names the companion tool to pair with ('Call repeatedly with aethis_refine_fields'). It lacks a negative case (when not to use it vs validate_fields), so it stops short of full routing guidance.

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