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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description must add beyond that — and it does, disclosing the lease prerequisite and that every call is recorded on the client as an integration event (an audit side effect). It does not cover error behavior or rate limits against the provider APIs it links to.

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?

The purpose and lease requirement are well front-loaded, but the tail is dominated by five provider documentation URLs plus a trailing API reference link. These are marginally useful yet consume roughly half the text and dilute the operative guidance an agent needs at call time.

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 4-parameter tool with a nested free-form query object and no output schema, the description covers purpose, precondition, scoping, and audit behavior well. It is silent on the shape of the response and on how read failures or pagination are surfaced, which an agent dispatching arbitrary provider endpoints would benefit from knowing.

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%, so task_id, provider, action, and query are already documented in the schema, including the native-path vs gateway-action distinction for 'action'. The description's parameter value-add is limited to listing example provider names, which the schema's own examples already mirror. 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 verb and resource ('one read-only (GET) call against a system this client has connected') and immediately grounds it with four concrete examples across providers. It cleanly separates itself from the write_integration sibling by emphasizing that it changes nothing in the provider.

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?

Gives a clear precondition (requires an active lease on a task; the task determines which workspace is reachable) and routes the agent to list_integrations to discover what is connected and allowed. It does not explicitly name write_integration as the counter-tool for mutations, leaving that inference to the 'changes nothing' phrasing.

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