Integration search

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

Beyond the readOnly/idempotent/openWorld annotations, it discloses result ordering ('matches best first'), the shape of each result ('each with its parameters (* = required)'), and the empty-result behavior ('no match says so'). That is meaningful behavioral context, though it says nothing about match quality thresholds or whether results are cached/stale.

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 purpose, then alternatives, then the follow-up tool, then an example — a sensible information order with no filler sentences. The domain enumeration is long but earns its place by bounding scope; a slightly tighter list would make it a 5.

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 an output schema present and full schema coverage, the description only needs to explain routing and result semantics, and it does both plus the call-chain to integration_call. The only omission is any hint about result-count behavior or what to do when matches are poor, which is minor for a two-parameter search tool.

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 is 3, and the description adds a concrete worked example ('print a PDF on the office printer') that clarifies the query parameter is a natural-language task rather than a keyword. The limit parameter is left entirely to the schema, which is acceptable.

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 description opens with a specific verb+resource ('Find a tool beyond the core set') and enumerates the concrete domains covered (devices, services, files, mail, printing, SSH, webhooks, playbooks, agents). It explicitly separates itself from skill_search and memory_search, so an agent can route without inspecting any schema.

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?

It states the use case (discovering non-core tools), names two sibling alternatives with the conditions that select them ('For how-to instructions use skill_search, for stored facts memory_search'), and names the follow-up action ('Run one with integration_call'). When-to-use, when-not-to-use, and alternatives are all present.

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