search_contacts

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful matching context (address book, WhatsApp name, company name, phone-number substring), but says nothing about result limits, ranking, or auth implications beyond the schema's limit note.

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?

A single front-loaded sentence stating verb, resource, and the two lookup modes with zero filler. Every clause earns its place.

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?

An output schema exists, so return values need not be explained, and the read-only nature is annotated. The description covers the search semantics well; the only real gap is the unexplained 'account' parameter.

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 67%: query and limit are documented in the schema, while 'account' has no description anywhere. The description's mention of 'nom d'entreprise' and 'carnet' adds a little meaning to the query parameter but does not compensate for the undocumented account parameter, so baseline 3 is right.

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 gives a specific verb ('Cherche') plus resource ('contacts') and spells out the two matching modes (by name or by partial number), so the agent knows exactly what the tool returns. It does not explicitly differentiate itself from neighbors like get_contact or check_whatsapp, so it falls short of a 5.

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 implied rather than stated: the agent can infer it should use this for fuzzy/partial lookups instead of fetching a single known contact, but no alternative tool is named and there are no when-not conditions. Adequate but with clear gaps.

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