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

Annotations already declare readOnlyHint, idempotentHint, and closed-world scope, so the safety profile is covered. The description adds real behavioral context beyond that: the accepted notation alphabets, the case convention for komal vs shuddha swaras, and that M denotes tivra — details an agent cannot infer from annotations and needs in order to build a valid query.

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 with the core behavior in the first clause, then the match semantics, then the notation reference. Dense but every element is functional; the long swara enumeration is the only mild weight, though it is genuinely needed for input construction.

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 two-parameter read-only lookup with no output schema, the description covers inputs well but says nothing about the response — e.g. whether results are annotated with which match type (exact vs superset) applied, or in what order they come back. Since no output schema exists, that omission falls on the description and is a real gap for an agent deciding how to use the results.

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%, so the baseline would be 3, but the description meaningfully extends the schema by explaining the notation grammar behind the `notes` string and how the two example forms ("S R2 G3 P D2" vs "S R G P D") relate to the Carnatic/Hindustani label systems. The `tradition` enum is left to the schema, which is fine given its self-documenting values.

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?

States a specific verb and resource ("Find the raagas that use a set of notes") and goes further by defining the two match modes returned: exact scale equality and superset inclusion. That reverse-lookup framing (notes -> raagas) is unmistakably different from siblings like list_raagas or find_raaga.

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 the use case (you have a note set and want matching raagas) and clarifies that both exact and partial matches are returned together, so no second call is needed. However, it never states when to prefer this over find_raaga or identify_raaga, nor any exclusions, so routing is left to inference from names.

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