mock_rule_create_from_entry

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

With no annotations, the description carries the full behavioral burden. It discloses mode semantics (patch vs fixture), that patch mode contacts the server while fixture uses the captured response, merge behavior (adds to existing rule, replaces on same pointer), host_scope handling, match_path coverage requirement, and that patches are validated against the entry. It does not cover error conditions or side effects beyond 'create or extend', but covers the key runtime behavior well.

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?

The description is long (~180 words) but justified for a 19-parameter tool. It front-loads the purpose and then systematically covers parameters. Some sentences, like the match_path example, are dense but add clarity. It could be slightly tightened, but it is well-structured and each sentence contributes to understanding.

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?

The description covers the core behavior and most key parameters, but leaves several parameters undocumented (priority, description, capture_id, recording_path, match_query_fields) and assumes the agent understands what an 'entry' is and how to obtain entry_id from sibling tools. Given the tool's complexity, an agent might need to consult other tools or schema for full context, but the description is adequate for the primary use case.

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?

Given only 21% schema description coverage, the description compensates by explaining most critical parameters inline: match_body_fields (with example), host_scope (any/exact/host glob), match_path (pattern semantics and example), mode, status, delay_ms, merge, request_patches, response_patches, and request_headers. It adds meaning beyond the schema, though a few parameters (capture_id, recording_path, match_query_fields, priority, description) remain unexplained.

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 opens with a clear, specific statement: "Create or extend the rule for one request variant (method + path + body/query values) from a captured entry." It names the verb ('create/extend'), the resource ('rule'), and the precise scope ('one request variant from a captured entry'), making it clearly distinguishable from siblings like mock_create_from_entry, which focuses on a different mechanism.

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 description gives extensive context on how to use the tool: it explains variant selection via match_body_fields, host_scope options, match_path patterns, mode differences, merge behavior, and status/delay overrides. It doesn't explicitly name alternatives or state 'when not to use', but it implies the use case (creating a rule from a captured entry) and provides enough guidance to select this tool for that purpose.

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