Find who the user means

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses the success shape (contact.chat_id plus number, note, tags, details, and context when writing) and the ambiguity/not_found policy. Gaps remain: 'see fix' is unexplained and it doesn't clarify account scoping behavior. Output schema covers the return payload, so this is solidly above baseline.

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?

It is short and front-loads the core resolution act, but the compression goes too far: sentence fragments and dangling references ('see fix') cost parseability. Space is saved at the expense of clarity rather than through it.

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 7-parameter, output-schema-backed lookup with strong annotations, the description covers resolution inputs, failure policy, write-session context, and the tag-listing mode. What's missing is a clear account_id/multi-account explanation and any note on limits, so it is good but not fully self-contained.

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 71%, so most parameters are already documented. The description reinforces tag listing ('tag: its people') and hints at qualifier disambiguation ('tells two apart' is in schema, not description), but it adds little on kind, limit, account_id, or include_context beyond what the schema states. Baseline 3 is appropriate.

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 states a specific job: resolve whatever the user said (name, nickname, relationship, filed detail, group, number, id) into a contact before drafting. It distinguishes itself from plain listing by framing this as 'who the user means', but the phrasing is telegraphic and it never names the obvious sibling (list_contacts) it replaces.

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 real usage context — call it 'before drafting', and on 'ambiguous or not_found: ask the user; never guess' — which tells the agent what to do when resolution fails. The 'Several accounts: see fix' branch points somewhere useful but the referent ('fix') is opaque and not a listed sibling, weakening the routing.

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