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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered without prose. The description adds genuine context beyond that — notably that visibility is bounded by what 'the saved token can see' and that sync recency and match counts are exposed — but says nothing about failure modes (no token saved, revoked token) or permission requirements.

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?

A single front-loaded sentence with the verb and resource up front and no filler. The parenthetical detail on sync time and matched-call counts is dense but earns its place; the trailing 'businesses you can link them to' clause is slightly vague but not wasteful.

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?

An output schema exists, so the description does not need to enumerate return values — yet most of its length is spent doing exactly that, and it stays silent on the required business_id, the action enum, and error states. For a low-complexity, 2-parameter read tool with full annotations this is passable but leaves the invocation surface under-described.

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% and the description never mentions either parameter, so it does nothing to compensate. The required business_id (uuid) and the single-valued action enum ['status'] are left entirely unexplained — an agent learns nothing about whether action must be passed, defaults, or what scope business_id controls.

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 and resource ('Read a business's Nimbata call-tracking setup') and enumerates the concrete data returned: connected account, project-to-business mapping with last-sync times and matched-call counts, token-visible projects, and linkable businesses. It never distinguishes itself from the obvious write counterpart (manage_nimbata) or the parallel get_lsa_setup, so it stops short of 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?

Usage is only implied by the enumerated payload — an agent can infer this is the diagnostic call to check whether call tracking is wired up and which projects feed a business. There is no explicit when-to-use statement, no 'do not use this to change settings, use manage_nimbata instead' exclusion, and no prerequisite such as a saved token existing.

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