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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description still adds substantial unique context: newest-first ordering, a 200-character snippet cap, the deliberate omission of the author, and an explicit statement that no lead/customer/message is created. The prompt-injection warning about the snippet being untrusted third-party text is exactly the kind of behavioral caveat structured fields cannot express.

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?

Front-loaded with the verb and result shape, then parameters, then guardrails — a sensible order for an agent scanning it. Dense but nearly every clause adds information; the closing two sentences on author omission and 'nothing is created' are the only slightly redundant prose.

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?

No output schema exists, yet the description compensates by enumerating the returned fields, and annotations cover the safety profile, making this close to self-sufficient. The remaining gap is the undocumented limit parameter and the absence of any mention of how many matches to expect or pagination behavior.

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?

With 0% schema description coverage the description carries the burden and does so for most parameters: status values and their meanings including null, account_id/account_uuid equivalence, and watch_id/watch_uuid narrowing. The only unexplained parameter is limit (default 50), which is left entirely to the schema; "newest first" implies ordering but not the cap.

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+resource ("Keyword matches a Telegram account found") and immediately differentiates scope from list_tg_watches / list_tg_targets by describing matches rather than watches or targets. It also enumerates the returned fields, so an agent knows exactly what this tool yields.

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 rather than stated: the default status=NEW ("not looked at yet") signals the intended triage flow, and the closing line says to summarise for the owner rather than act. But no sibling is named as an alternative (e.g. list_tg_watches to see watches first, mark_tg_match to advance status), so routing between tools must be inferred.

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