salesforce_search_contacts

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

Annotations already signal readOnlyHint=false, destructiveHint=true, openWorldHint=true, and idempotentHint=false. The description adds no behavioral details beyond the routing mechanism; it doesn't disclose potential side effects, whether the action might modify data, or any rate limits or auth constraints beyond the mentioned JWT/tenant/company scope. The destructiveHint annotation is surprising for a 'search' action, and the description neither clarifies nor contradicts that, so it misses an opportunity to explain an important safety nuance.

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 description is compact and front-loaded with the key action, followed by routing context and an argument list. No filler or repetition exists. It earns its length, though a brief example or a clearer restatement of purpose would improve it without adding bulk.

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?

The tool is a thin passthrough to a domain-agent action, but the description does not explain what this action actually does with 'search_contacts', what input structure is expected, what output to expect (even though an output schema exists), or when it should be selected over similar contact-related tools. Given the wide sibling list and the odd destructiveHint, an agent cannot safely decide to call this tool with confidence.

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?

The schema has 0% description coverage, and the description provides minimal glosses: 'message: Free-text objective' and 'inputs: Optional JSON string of structured inputs.' This is better than nothing but still deeply generic. It gives no indication of what fields the JSON 'inputs' should contain for a contact search, what message phrasing is effective, or how the two parameters interact. It partially compensates for the schema gap but leaves the agent guessing about actual usage.

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 says 'Run the salesforce domain agent action `search_contacts`.' This names the action and identifies the resource (Salesforce contacts) via the tool name, but it never explicitly states that the tool searches for contacts or what kind of results it returns. It doesn't differentiate itself from sibling tools like list_crm_contacts, salesforce_get_contact, or salesforce_soql_query; the agent can infer the purpose from the name, not from a clear statement of behavior.

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?

There is no guidance about when to use this tool versus alternatives. The description only mentions routing through the domain-agent dispatcher under JWT, tenant, and company scope, which is context about invocation, not usage criteria. Siblings like list_crm_contacts and salesforce_get_contact exist, but the description does not explain how search_contacts differs or when to choose it.

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