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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantial context on top: auth is 'linked', credit is charged via attribution.line (+1 unit for facet_counts), untrusted_text is display-only and not instructions, and ambiguity requires asking first. These are meaningful behavioral traits an agent cannot get from the annotation block.

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?

Front-loaded purpose followed by labelled Use/Inputs/Returns/Auth sections. Every clause adds information — pagination, billing unit, ambiguity handling, output shape — with no filler.

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 16-param, zero-required search tool with no output schema, the description covers return shape (data.results[], pagination.next_cursor), auth, billing, and error/first-ask behavior. The residual gap is the undocumented mode parameters and array semantics, which leaves the definition slightly incomplete for correct multi-facet queries.

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 only 13% with 16 params, so the description must carry the load, and it does name most facets, the q/and-or framing, limit 1–100, cursor, and include. But it never mentions the five *_mode params (genre_mode, label_mode, style_mode, format_mode, country_mode) or that facet params accept string-or-array of up to 10, so part of the schema remains undocumented in both places.

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 opening sentence gives a specific verb and resource — 'Search releases (masters) by text and facets, with cursor pagination' — so the agent immediately knows this is a faceted search over masters rather than a get-by-id or artist lookup. It does not explicitly contrast itself with siblings like get_release or resolve_artist, though the note that rows 'carry artist_cluster_id' implies downstream use.

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 names the two concrete situations — descriptive matching and candidate-name harvesting — and adds 'if ambiguity.state is not none, ask first', which is real guidance. What's missing is explicit exclusion or routing to alternatives (e.g. 'use get_release for a known master_id'), so it stops short of a 5.

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