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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely new behavior: newest-first ordering, id scoping per number ('an id from another number answers not found'), pagination contract, and retention semantics where old content returns an empty preview with content_expired true while the message, sender and group remain listed 12 months.

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 short paragraphs, front-loaded with purpose before filters, paging and retention, with no wasted filler. Slight redundancy with the already-descriptive schema parameter docs (cursor, number_alias) keeps it from a 5.

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 six-parameter, zero-required listing tool with an output schema, everything needed for correct invocation is present: filtering model, pagination protocol, cross-number constraint, and the retention edge case that explains apparently empty previews. Return-value detail is delegated to the output schema, as expected.

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 earns one extra point by framing the semantics of filter combinations conceptually ('group_id with contact_id answers what one person said in one group') and by stressing that the same number_alias must be reused for ids and cursors. Much of the rest (group_id, contact_id, direction, cursor) restates the schema descriptions, so it does not exceed that.

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?

Opens with a specific verb and resource plus scope and ordering: 'List messages for one number, newest first, received and sent.' It then explicitly contrasts itself with get_message ('Mentions, transcription and full media detail are only on get_message'), so an agent can separate this list tool from the single-message sibling without opening either schema.

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?

Gives concrete routing rules and conditions: use this for enumeration, call get_message for the one message whose detail you need, resolve a group's grp_ id via list_groups, use contact_id for what a contact sent or received, direction to restrict to inbound/outbound, and note that filters combine. It also states the cross-number failure mode and the cursor-plus-same-filters requirement for paging.

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