list_leads

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description does not contradict this. It adds valuable behavioral context: 'Newest activity first by default', 'Filter by status / assignee / tags / created-at range / keyword / whether they have an upcoming booking', and critical notes about server-side matching with masked emails and the half-open pagination/filtering behavior for hasUpcomingBooking. These details go beyond the schema and annotations, ensuring the agent knows exactly how filtering and data masking behave.

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 description is well-structured: it opens with the primary function, then describes typical return contents and default sorting, followed by filtering options and important usage caveats. It is moderately concise, with every sentence adding value (e.g., the note about never guessing codes and the leadId/examineeId distinction). Some redundancy exists (filter list partially repeats schema), but overall it is efficient and front-loaded.

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?

Given the tool has 10 parameters and an output schema exists, the description does not need to explain return values. It covers the key operational aspects: scope, default sort, filtering options, and essential preconditions (calling list_lead_settings). It also discloses the hasUpcomingBooking filtering nuance. Minor gaps include no mention of pagination behavior beyond the schema (though page/limit are self-explanatory in the schema) and no explicit note on performance/limits, but these are adequately addressed by the schema and annotations.

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 schema description coverage is 100%, so the baseline is 3. While the description reinforces some param semantics (e.g., the need to use codes from list_lead_settings for status and tagCodes, and that keyword matches the real email server-side despite masking), it does not add significant meaning beyond what the schema already provides. The schema descriptions themselves are detailed, and the tool description offers only marginal additional parameter insight.

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 clearly states the tool lists CRM leads for the current team, describes the fields returned (follow-up status, assignee, colour tags, submission count, next booking), and specifies default ordering. This differentiates it from siblings like list_records and get_lead, which have different purposes. The verb 'list' is specific and the resource is defined without ambiguity.

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?

The description provides actionable guidance: call list_lead_settings to obtain valid status/tag codes and never guess, reference leads by leadId and respondents by examineeId. It also clarifies the scope ('of the current team' and 'across all forms'). While it does not explicitly mention alternative tools or when not to use this tool, the context is clear enough for an agent to decide when to invoke it.

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