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

Beyond the readOnly/idempotent annotations, it discloses the over-merge signal, the credit attribution.line requirement, the instruction to ask before proceeding when ambiguity.state is not none, and that untrusted_text is display-only. These are exactly the behavioral facts an agent cannot infer from annotations or schema.

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?

Structured as Purpose/Use/Inputs/Returns/Credit/Auth — front-loaded and dense with no filler. Some phrasing is jargon-heavy ('hosaka's over-merge signal', 'crate flags one') and costs a line of clarity, but nothing is redundant.

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 adequately covers return shape (label facets plus ambiguity.state), auth (linked), and attribution obligations. Minor residual gap is that 'facets' is left undefined, so the agent does not know exactly what fields to expect.

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 schema only says string of 1-200 chars, so the description carries the burden: it defines `key` as a label cluster_id (64-hex) or a crate slug. That is substantive, though it does not explain what happens if the format is wrong or which form is preferred.

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?

Names a specific resource (record-label card with identity and allowlisted facets) and implicitly the retrieve verb. It is clearly distinguishable from get_artist and get_release among siblings, though the verb itself is only implied by the name rather than stated.

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 'Use:' line gives two concrete triggers: the user asks about a label, or an artist card names a label to expand. That is clear invocation context, but no explicit exclusions or named alternative tools are offered for ambiguous cases.

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