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

Annotations only declare readOnlyHint=true, so the description carries real additional weight: it discloses the data sources the result is derived from, that each item includes its reason and provenance, and that `readiness` can be 'pending' or 'partial' — in which case the agent must caveat a short list rather than present it as complete. That staleness/completeness contract is behavior an agent could not infer from structured fields.

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?

The purpose and computation sources are front-loaded in the first sentence, followed by the enumeration, the trigger phrases, and the readiness caveat in descending priority. It is dense but every clause — provenance, card rendering, staleness — carries operational information.

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 steps in to describe the return shape ('each item carries the reason and where the numbers came from') and the readiness field's meaning. Combined with the presentation contract, an agent has everything needed to call and correctly surface this tool.

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 both `kinds` and `limit` are already documented, including the enum values and default/max on limit. The description's enumeration of item kinds loosely maps to the `kinds` enum but adds no syntax or filtering guidance beyond the schema, so the baseline of 3 applies.

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 a concrete deliverable (an attention list computed from sent mail, calendar, LinkedIn export and set follow-ups) and enumerates the eight item kinds it can surface. It also distinguishes itself from per-person lookups by specifying it applies when the user does NOT name one person, which separates it from siblings like get_person_card or quiet_contacts.

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?

It gives explicit trigger phrases ('what needs my attention', 'who am I forgetting', 'who should I follow up with', 'what should I do today') plus a general rule for anything asking who to deal with without naming a person. It also states the required follow-through: render an attention_list card and do not reproduce the items in text.

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