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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description is not burdened with safety. It adds genuine context beyond them: it returns personal data (PII disclosure), omits transcripts, sorts newest-first, and discloses cursor-based pagination. That is solid behavioral value on top of the annotations.

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?

Four front-loaded sentences: purpose, returned fields, filtering/paging, and the PII/transcript caveat. No padding, and the most decision-relevant information (what it returns and how to filter) comes early. The 'Read-only' tail is redundant with annotations but harmless.

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 7-parameter, no-required read-only list tool with no output schema, the description covers the decision-critical surface: what is returned, PII handling, ordering, filtering, and pagination. Remaining gaps (limit, query override, brand_id) are minor given the annotations already carry the safety profile.

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 low (29%), so the description must compensate. It clarifies stage filtering, the 'captured at or after' semantics of since (beyond the schema's bare date-time format), and paging via cursor. But limit, query, and brand_id are left unexplained, and the description calls the cursor 'next_cursor', which does not match the actual parameter name 'cursor'.

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 ('List leads the AI DM agent captured in the selected workspace') and adds scope details (newest-first ordering, returned fields, and the note that transcripts are excluded). The explicit 'without the conversation transcript' implicitly separates it from aidelly_get_inbox_items and aidelly_get_inbox_lead, so an agent can route without opening schemas.

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?

Provides filter guidance ('Filter by stage or by since (captured at or after)') and pagination guidance ('follow next_cursor for more pages'), which is implied usage. However it never names a sibling alternative (e.g. get_inbox_lead for a single lead) or states when-not to use this tool, leaving tool selection to inference.

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