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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuinely useful context beyond them: the default sort order, the alternative order, and the shape of returned records including state values (new, call_back, won, lost, archived), category, scheduled call back, claimant, and lead_data. It stops short of 5 because it doesn't describe pagination behavior or the total/next_page semantics of the reply.

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 dense sentences with ordering front-loaded and no filler; the field inventory is compact. The trailing 'GET /lists/{id}/leads' is mild redundancy with the name and annotations but still reinforces the read semantics in few characters.

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 no output schema, the description usefully compensates by enumerating the returned lead fields and the possible state values, and it documents the two ordering modes. Pagination behavior (page/per_page, next_page) is left entirely to the schema, which is acceptable given its 100% coverage but is the one remaining gap for a paged list endpoint.

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 100%, so list_id, page, per_page, and the order enum are all already documented in the schema, including defaults and the next_page handoff. The description only restates the order semantics, adding no syntax or format detail beyond the structured fields, so the baseline of 3 applies.

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 the resource and its scope precisely: leads belonging to one list, with explicit default ordering and the order=last_updated_first alternative, plus the fields each lead carries. The verb is implicit (no 'list/return' verb, only the trailing GET endpoint), and it does not distinguish itself from siblings like myphoner_find_leads or myphoner_search_leads, 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 implied: it requires a list_id and returns that list's leads, so an agent can infer it is the correct tool when the list is already known. However, there is no explicit statement of when to prefer it over find_leads/search_leads (e.g., 'no filtering by user/state; use search_leads for that'), and no exclusions or prerequisites.

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