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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description adds the non-obvious authorization requirement 'Requires leads:read', which annotations cannot express. It does not disclose count freshness or whether counts are workspace-scoped, but the safety picture is fully covered elsewhere.

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 short sentences, front-loaded with the output content and followed by the permission and usage cue. No filler, nothing redundant with the annotations.

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-parameter, read-only tool with no output schema, the description effectively tells the agent what the response contains (four named counts). Minor gaps: the timezone/definition of 'today' and whether counts span the whole tenant or a narrower scope.

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?

The tool takes no parameters, which is the baseline-4 case; nothing about invocation needs explaining beyond the empty schema. The description correctly implies no inputs are needed.

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 set: it returns counts of contacts, customers, follow-ups due today, and unread enquiries. That distinguishes it from list_contacts and list_enquiries (which return records, not aggregates), though it never names those siblings explicitly.

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?

'Use this to answer “any new leads?”' gives a clear, concrete situation for selecting this tool over the list tools. It stops short of explicit when-not guidance or precondition detail, so it is strong context but not full routing logic.

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