exposure_check

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

With no annotations provided, the description carries the full burden and it delivers the key behavioral traits: 'Read-only, no auth' discloses the safety profile and permission requirements. 'Evidence cites lifetime + recent counts' explains the data basis of the output. It stops short of covering edge-case behavior (unknown subject, invalid user), but for a read-only query tool the essential traits are disclosed.

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?

Two sentences and a parenthetical, with no wasted words: purpose first, then evidence basis, then safety trait, then the routing hint. Each clause earns its place and the most decision-relevant information (what the tool does) is front-loaded.

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?

For a read-only, 4-parameter lookup with no output schema and no annotations, the description plus 100%-covered schema cover the essentials: purpose, the five output tiers, evidence basis, auth requirements, and preference for the canonical sibling. The response_format parameter addresses return shape. Missing is any note on error behavior or what happens for subjects outside the user's listening history, but the definition is largely complete for correct invocation.

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 the parameters are already well documented (subject_type enum with default, response_format enum explaining each value, statsfm_user clarifying no auth needed). The description adds domain framing — the exposure ladder levels and lifetime/recent counts — which enriches meaning but doesn't add syntax or format details beyond the schema. Baseline 3 is appropriate given the schema carries the load.

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 identifies the resource (exposure ladder with the five named levels: unheard / sampled / explored / established / favorite) and what kind of answer the tool produces. The verb is implied rather than stated declaratively ('Where does a subject sit...'), and it distinguishes itself from siblings by naming statsfm_exposure_check as the canonical counterpart. A direct 'determines the exposure tier of a subject' would push this to a 5.

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 an explicit routing instruction: 'Legacy alias of statsfm_exposure_check — prefer the canonical name,' telling the agent which sibling to prefer. Combined with 'Read-only, no auth,' the agent knows this tool is a safe, credential-free lookup. It does not offer guidance on when to choose exposure checking over other related taste/ladder tools (e.g., taste_obsession_ladder), so the guidance is present but narrow.

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