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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds something the annotations cannot: that results are ids intended for a follow-up fetch, which is the key behavioral fact given there is no output schema. It stops short of mentioning result limits, ranking across entity types, or whether all three resource types are searched in a single call.

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?

Two short sentences, front-loaded with the verb and resource scope, with the downstream fetch hint last. No filler, no repetition of the title or annotations.

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 one-parameter read-only search with no output schema, the description covers what is searched, what keys are accepted, and what comes back (ids for fetch). The main omission is any hint about result volume or cross-entity behavior, which matters slightly more here because the tool spans three resource types at once.

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 a single parameter with 100% schema description coverage, so the schema already carries the burden of explaining 'query'. The description's enumeration of name, phone, email and spoken words marginally broadens the schema's 'A name, number, email address or words', but adds no syntax, formatting or matching-behavior detail beyond it.

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 set: searches the CRM across merchants, text threads and calls, and names the lookup keys (name, phone, email, spoken content). It does not, however, distinguish itself from the narrower siblings search_calls, search_leads, search_emails, search_texts and search_what_was_said, so an agent cannot tell from the description alone why it would pick this broad search over one of those.

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?

The clause 'Returns ids to pass to fetch' gives a useful two-step workflow hint for what to do after the call. But there is no statement of when this unified search is preferable to the entity-specific search siblings, and no exclusions or prerequisites, leaving the alternative-selection decision to inference.

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