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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed world, so safety is covered. The description adds genuinely non-obvious context: results are chronological, limited to a bounded recent window, and deleted messages surface as markers rather than being dropped. It does not clarify what the bound actually is or how pagination terminates, so it adds value without delivering a full behavioral picture.

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?

A single dense sentence with the scope, ordering and key capabilities front-loaded; every clause carries information. It reads as a fragment rather than a sentence, but there is no filler wording.

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 and no parameter descriptions, the description should carry more weight. It covers ordering and tombstone behavior but leaves open the pagination cursor semantics, the default and maximum limit behavior, and the fact that project_id is mandatory and scopes the whole result set.

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 0% across 5 parameters, so the description must compensate and only partly does. 'Literal body search' usefully tells the agent that search is exact-text, and 'threads' and 'pagination' loosely map to reply_to and limit/before_seq, but none of the parameters are named and the relationships (e.g. whether reply_to includes or excludes the parent) stay ambiguous.

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 names the resource (messages) and its scope: recent, chronologically ordered, bounded window, with search/threads/pagination support. That is specific enough to distinguish it from get_message (single retrieval) without opening a schema, though it omits an explicit verb and the word 'recent' is undefined.

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 only implied: list-style retrieval with search and thread filtering, versus get_message for a single message. There is no explicit when-to-use or when-not-to-use statement, and no mention of how it relates to siblings like get_inbox or list_participants.

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