SensorTower vocabularies (offline)

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

Annotations already cover readOnly/openWorld=false/idempotent, so the bar is lower; the description adds value by confirming 'Entirely offline: 0 requests' and disclosing that the static JSON files the contract links to are dead. It could say more about output size/shape, but the extra behavioral context is genuine and non-duplicative.

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 content scope, then the facets mapping, then the offline/usage note. It is dense but each clause carries distinct information; slightly packed but no filler sentences.

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 zero-request static reference tool with a single fully-documented enum parameter, the description covers content, usage, and the offline guarantee adequately. No output schema is needed for a vocabulary dump, though a hint on output size/shape would have made it complete.

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% with an enum on the single `section` parameter, so the schema already documents the narrowing options fully. The description does not add meaning beyond the schema for `section`, so the baseline 3 applies.

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 resource (offline vocabularies: category ids, chart types, ad networks, tags, sentiments, keyword types, audience formats, metric-to-breakdown table) and its use. It clearly distinguishes itself from the data-fetching siblings by being the enum/reference source, and even explains the facets path-key mapping. An agent can tell exactly what it gets.

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?

Explicitly instructs 'Read this before guessing an enum' and warns that linked /api/docs/static/*.json files are dead, giving a concrete when-to-use trigger and when-not (don't guess, don't chase the dead static files). The zero-request note reinforces that this is the cheap, safe lookup path.

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