rew_search_api

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful scope information ('ALL REW operations', with the domains enumerated), but says nothing about the result shape, result ordering, or the cost of very broad searches. It adds moderate value on top of the annotations without extending into behavior.

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, front-loaded with the action and scope before the domain enumeration. The domain list is long but pays for itself by telling the agent how broad the search surface is. Only minor trimming would improve it.

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?

This is a read-only search tool with no output schema, so the description should at minimum convey what a hit is and how paging works; neither is covered. The 0% parameter coverage and the unexplained refresh flag leave real gaps, though the broad-coverage statement does help the agent understand the search space.

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% for six parameters. The description gives a loose gloss for three of them ('words' for search, 'category tag' for tag, 'HTTP method' for method) but never names them or explains matching semantics. The pagination pair (limit/offset, with defaults 30 and 0) and, more importantly, the refresh boolean are completely undocumented, leaving an opaque cache-invalidation flag for the agent to guess at.

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 (Search) and resource (ALL REW operations) plus the three facets it can search by: words, category tag, and HTTP method. The catalogue of covered domains (audio devices, measurements, EQ, alignment, etc.) makes the scope concrete. It does not name a sibling or say how it differs from rew_describe_api or rew_call_api, which keeps it from 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 word 'Search' plus its position relative to siblings implies a discovery/lookup step before acting on an operation, but the description never states when to use this rather than rew_describe_api or rew_call_api, and gives no exclusions or prerequisites. Usage is inferred, not prescribed.

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