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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description only needs to add value beyond that. It adds useful interpretive context—shape tokens alone cannot explain a context/volume score, and similarity is not a probability—while also sketching what the explanation contains. It stops short of detailing response format or client-side behavior, but the added caveats are meaningful.

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 three short sentences with no filler, and the main deliverable is front-loaded in the first phrase. It is compact but jargon-heavy—p10/p50/p90, anatomy-token observations, and context/volume score may be opaque to a new agent—which slightly reduces clarity without bloating the text.

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 partially covers return content by naming distance, anatomy-token observations, and outcome vs neighbours, while annotations cover the safety profile. However, it does not describe response structure, edge cases, or how the many optional parameters affect behavior beyond what the schema states, so an agent would need to infer some behavior from the schema and sibling tools.

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 100%, with enums, defaults, ranges, and format constraints documented for all 11 optional parameters, so the description does not need to repeat them. Phrases like 'ranked,' 'reported method,' and 'neighbour p10/p50/p90' add some conceptual context to rank and limit parameters, but no parameter-specific semantics beyond what the schema already provides. Baseline 3 is appropriate.

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 names a specific deliverable—an explanation of why a candle 'twin' ranked under the reported retrieval method—and enumerates the evidence types considered: distance, anatomy-token observations, and outcome vs neighbour p10/p50/p90. It avoids tautology and makes the tool's scope clear, though it does not explicitly distinguish it from siblings like inspect_candle_analogue or get_candle_evidence_board.

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 implies when the tool is relevant: explaining a match ranking, not predicting direction. It also provides a negative guard with 'Similarity is not P(direction).' However, it never names an alternative tool or offers explicit when-to-use/use-this-instead guidance, leaving sibling selection largely to inference.

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