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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds genuine non-obvious behavior: logging bumps the contact to the top of the list, a side effect the agent would not otherwise know. It doesn't state validation or failure behavior, keeping it below 5.

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?

Three short sentences with no filler. The core action leads, and the side effect is appended only after the primary purpose is clear.

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 three-required-parameter write tool with full schema coverage and no output schema, the description covers purpose, kind options, and a key side effect. Remaining gaps (error behavior for an invalid contact_id, duplicate handling) are minor and partly carried by the schema.

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 schema already documents all three parameters, making 3 the baseline. The description's enumeration of kinds loosely maps to the 'kind' enum ('text' vs. the actual 'sms' value), which is a minor but not harmful addition.

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 ('Add a note, call, voicemail, meeting or text to a contact timeline') and enumerates the activity kinds, so the agent knows exactly what gets created. It does not name the closest sibling (log_outreach), so differentiation is only implicit through the 'already happened' framing.

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?

'This is how you record something that already happened' gives an implied when-to-use rule, contrasting past-tense logging with presumably forward-looking create_task work. However, no sibling is named and no exclusion is stated, leaving the agent to guess between this and log_outreach for outbound contact records.

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