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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description confirms read-only while adding behavior the annotations cannot: ambiguous-name resolution returns found=false with candidates, and the memory record itself is preserved when attaching a fact. No auth, rate-limit, or pagination behavior is disclosed, but for a read tool the added context is substantive.

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 lead clause is well front-loaded, but the body is one very long sentence that chains a data inventory, a nested workflow instruction, and the disambiguation rule without separation. Every piece of information is relevant, yet the run-on form makes scanning harder than it needs to be.

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?

There is no output schema, so the description must describe returns, and it does so thoroughly across nine content categories plus disambiguation and suggested_facts handling. The only substantive omission is the 'interactions_limit' parameter's meaning and effect on the timeline, which keeps it at 4.

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 0%, so the description carries the burden. It explains 'contact_id' and clarifies that 'query' is a name, which is genuinely additive, but 'interactions_limit' is never mentioned despite bounding the returned timeline (1-50). Two of three parameters are covered, leaving a visible gap.

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 ('get ... one person' from the caller's OWN contact book) and then enumerates the exact payload: card, who_is, relations, linked leads/notes/tasks, timeline, birthday, keep-in-touch state, reminders, suggested_facts. The 'OWN contact book' scoping plus the enumerated contents clearly separate it from siblings like who_is, person_brief, and hr_get_person.

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?

Gives real lookup guidance: supply 'contact_id' or a name 'query', and if several fit, handle found=false with 2-3 candidates by asking the user and never guessing. It also routes the suggested_facts follow-up to add_person_interaction(kind=fact, source_ref='memory:<memory_id>'). It stops short of explicitly contrasting with who_is or person_brief, so a 4 rather than 5.

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