contacts_search

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

With no annotations, the description carries the full burden, and it does disclose two genuinely non-obvious behaviors: a hard page_size ceiling of 30 from the upstream API and an automatic single retry on a cold search index. That is useful context an agent could not get elsewhere. However, it says nothing about result ordering, whether pagination beyond the first page is possible, or what the account parameter authorizes, which are material gaps for a tool with zero annotation coverage.

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 the core purpose front-loaded, followed by the constraint and then the retry quirk. Every sentence carries information, though the closing clause "so the caller never has to" is slightly conversational padding that could be dropped.

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 simple three-parameter search with no output schema and no annotations, the description covers the operational quirks well but leaves two required-parameter semantics and the pagination contract unaddressed. An agent could call it, but would be guessing about `account` and about what happens with results beyond the page size.

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% across three parameters, so the description must compensate and only partly does. It clarifies page_size's maximum and implies query matches name/email/phone, but the required `account` parameter is never mentioned at all, leaving an agent to guess whether it is an email, an alias, or an account ID. It also omits the default page_size value and any query syntax rules (exact vs. substring).

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 opens with a specific verb and resource ("Search saved contacts") plus the matched fields (name/email/phone), which is more than a restatement of the tool name. It does not explicitly distinguish itself from siblings like contacts_list or contact_get, so an agent must infer that this is the query-based path, but the purpose itself is unambiguous.

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?

Usage is only implied by "search by name/email/phone"; there is no explicit statement of when to prefer this over contacts_list (enumerating all) or contact_get (fetching one known contact). The retry note tells the caller they don't need to handle the cold-index case, which is a small piece of operational guidance, but no exclusions or alternatives are named.

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