search_for_steps

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the filtering semantics, the empty-returns-all default, and crucially that the library is derived from the transpiler's STEP_PATTERNS so it 'exactly matches what transpile / run_scenario execute'. It doesn't state whether the result is cached or how large the library is, but the key behavioral guarantees are present.

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?

Front-loaded with purpose and efficient overall, but it is one dense paragraph and the final sentence restating the return object duplicates what the output schema already defines. Slightly more padding than necessary.

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 restating return values was optional, yet the description otherwise covers the gaps that matter: purpose, filter behavior, provenance, and usage. Complete enough for an agent to call correctly, with only minor redundancy.

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 0% (the single 'keywords' param is documented only as a bare string with a default), so the description must compensate and does: 'each whitespace-separated token must appear, case-insensitive; empty returns all'. This fully specifies the filter semantics an agent needs.

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 the supported Gherkin step vocabulary' / 'the qa-mcp step library') and enumerates what each entry contains. It clearly separates itself from siblings like transpile and run_scenario by describing what this tool provides versus what those execute.

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?

Explicitly names the use case ('Use it to author features for qa-mcp') and explains the relationship to the alternative ('transpile then flags any unmapped lines'). It gives clear context but stops short of stating when-not to use it or naming other search alternatives.

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