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

Annotations only supply readOnlyHint=false; the description adds the crucial async contract: it queues work and returns immediately, the email lands in a minute or two, and the agent should say it is 'on its way' rather than 'arrived'. It also discloses that delivery overrides the disabled daily-email setting, which is behavior an agent could not infer from annotations or schema.

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?

Dense and front-loaded: action, triggers, content scope, async behavior, and the focus caveat each occupy one clause with no filler. Nothing repeats the schema or annotations.

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 still covers everything needed to invoke and report correctly: what gets sent, what it contains, that it is queued asynchronously, and how to phrase the confirmation to the user.

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% for the single focus parameter, so the baseline is 3, but the description adds conditional invocation semantics ('Pass focus only when they name a topic to lead with') that the schema's 'in the user's words' phrasing does not convey.

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 ('Write the user's Daily Briefing now and email it to them') and scopes the content ('what is new since the last briefing they were sent'). This clearly separates it from generic siblings like send_email or draft_email_in_gmail.

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?

Provides explicit trigger utterances ('send me my daily briefing', 'brief me', 'email me my briefing') plus the governing condition 'when they ask for it', and notes it fires even when the daily email setting is off. The conditional rule for the focus parameter ('only when they name a topic') is also a usage constraint.

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