Count unread insights

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

Annotations already declare readOnly/openWorld=false/idempotent/destructive=false, so the safety profile is covered. The description adds material context beyond them: required scopes (analytics:read, luca:read), data sensitivity 'redacted', and the fact that no idempotency key is required. This is useful operational context not present in the structured fields.

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 human-readable purpose leads, then a compact metadata block covers operation, scopes, idempotency, and workspace override. Every line carries information, though the boilerplate-style metadata block is somewhat verbose relative to the tiny operation.

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, return-value explanation is rightly omitted, and annotations cover the safety profile. The description supplies scopes, sensitivity, cost/polling guidance, and parameter fallback semantics, so an agent has what it needs to call it correctly; only explicit sibling routing is missing.

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. The description goes slightly beyond the schema by explaining that workspaceId/workspaceSlug override 'the default workspace configured by environment,' which clarifies the fallback behavior the schema alone does not state.

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 gives a precise verb + resource: 'How many insights the coach has not read yet.' That is unambiguous and clearly distinct from the mutation siblings (mark_read, dismiss, mark_actioned). It does not explicitly name an alternative, but the count-vs-mutate distinction is evident.

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?

'Cheap enough to poll before pulling the whole feed' is a genuine when-to-use hint, and the workspace-override note gives a calling condition. However, no sibling is named as an alternative (e.g. versus luca_analytics_insights or the full feed tool), so guidance remains implied rather than explicit.

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