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

With annotations already covering openWorld/idempotent/destructive, the description still adds what the annotations cannot: the message goes out as an email from the signed-in user, replies return to the account email, confirm records user approval, a daily send limit exists whose error is not retry-clearable, and secrets must not be included. 'Works on read-only connections because it changes nothing in the account' is scoped to the account and is consistent with openWorldHint=true (the side effect is outward, via email), so it does not contradict readOnlyHint=false.

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 action, then layered constraint by constraint; every sentence carries distinct information (recipients, confirm, content quality, rate limit, secret warning). It is slightly long for a three-parameter tool and the read-only-connection sentence partially restates the 'changes nothing' idea, but there is no filler.

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 send-side tool with three required params and an output schema, this covers everything an agent needs: what the tool does, what not to use it for, what happens downstream (email + reply routing), approval semantics, failure mode, and the security constraint. Return values are handled by the output schema, so nothing critical is missing.

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 the enum meanings for topic, the 10–5000 char bounds for message and the confirm semantics are already fully documented. The description largely echoes these (confirm 'records that the user approved the exact topic and text') and adds only message-quality guidance; the dashboard_url it mentions is not even a parameter, so it adds little parameter semantics.

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 a specific verb and resource ('Send a message to the notolens team') and immediately scopes it: it is about notolens itself (service, dashboard, these tools), not about a match. That exclusion cleanly separates it from the match-oriented siblings like get_match, summarize_matches and start_takedown.

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?

Explicit when-to-use via the three topics (question/feedback/bug), an explicit when-not ('not about a match'), plus content guidance ('stating what the user did and expected, plus any dashboard_url'). It also names the conditions under which the call fails (daily message cap) and that a retry will not clear it.

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