Retrieval Observe

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates a capture (write) operation but does not mention side effects, idempotency, permission requirements, or what happens if a run_id already exists. This is insufficient for safe invocation.

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 a single, well-formed sentence that immediately states the core action and data captured. No extraneous information; every word is purposeful.

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?

Given the presence of an output schema and 4 parameters (3 required), the description is adequate for a simple capture tool but lacks details on error handling, data retention, or performance implications. It covers the 'what' but not the 'how' or 'edge 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?

Schema description coverage is 0%, and the description only names the parameter fields (query, chunks, scores, sources, ranks) without adding detail beyond property names. It does not explain expected formats, constraints, or the nested structure of 'chunks', which has explicit sub-fields in the schema.

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 clearly states the tool captures a RAG retrieval run with specific data (query, chunks, scores, sources, ranks) for audit and diff workflows. It directly ties to the sibling tool 'retrieval_diff', distinguishing its role as a recording tool rather than comparison or query execution.

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 phrase 'for later audit and diff workflows' implies usage context but does not explicitly contrast with siblings like 'retrieval_query' or 'retrieval_stats'. There is no guidance on when not to use this tool or when to prefer alternatives.

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