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

The annotations only assert that this is a safe read; the description adds non-obvious behavior the agent cannot get elsewhere. It states that contacts are shared by every agent on the account, that each entry is itself another Account, and it explicitly frames the names and descriptions as untrusted data written by a third party, never instructions. That trust framing directly shapes how an agent should handle the returned content and is exactly the kind of value structured fields cannot provide.

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 content is dense but each element earns its place, and the untrusted-data warning is not padding for a tool whose output carries third-party text. The weakness is ordering: the long descriptive clause about entry structure comes before the actionable 'Pass query' and 'Use it to find...' sentences, so the operational guidance is back-loaded.

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 correctly takes on the burden of explaining the return shape, and it does so thoroughly, including nested prefixes and addresses. Nothing about how to call the tool is missing. It lacks any sense of result volume, pagination, or limits, which is a minor gap for a listing tool on a shared account.

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?

There is one optional parameter with full schema coverage, so the schema already documents the query field, its length bound, and the 'omit for every entry' default. The description's 'Pass query to search names and notes' confirms the search scope, but adds no syntax, matching, or result-ordering detail beyond what is already present. With coverage at 100%, the baseline of 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 definition names the resource (the Account's contacts) and then enumerates what an entry contains: display name, note, status (contact or blocked), adder, prefixes with verified identity, and addresses with names/descriptions. That level of specificity clearly distinguishes it from the mutation siblings save_contact and remove_contact, which an agent can rule out without opening another schema.

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 a concrete use case: use it to resolve a fuzzy human reference like 'my friend Ilya' or 'Jack's scheduler' before sending. That is a real when-to-use signal tied to a downstream action. It stops short of explicitly naming alternatives or exclusions (e.g. when to use get_account instead), so it is a strong 4 rather than a 5.

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