contacts_read

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

The annotations already establish read-only, idempotent, non-destructive behavior, so the description adds useful domain context: contacts group a person's conversations, get returns channels and consent, timeline returns conversations in order, and audit_log returns merge/unmerge/consent history. It does not cover pagination behavior or rate limits, but it adds substantive behavioral detail beyond the annotations.

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 front-loaded with the core definition and then structured with pipe-separated action descriptions. It is dense but efficient for a multi-action tool, with no clearly wasted sentences, though the repeated 'Needs: identityId' phrasing makes it slightly compressed.

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 an 8-parameter, 4-action read tool with no output schema, the description covers the identity model, sibling differentiation, action meanings, and conditional ID requirements. Pagination and mode behavior are left to the schema, which is reasonable, but a little more detail on list results or pagination expectations would make it fully complete.

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?

With 50% schema description coverage, the description adds important meaning by defining each action value and the conditional requirement for identityId on get, timeline, and audit_log, plus search for list. It leaves page, limit, mode, and multiChannelOnly to the schema, which already documents most of them, but the action and conditional-ID semantics are key additions.

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 opens with a specific verb and resource ('Read contacts (identities)') and immediately defines the domain object as one person recognised across channels. It explicitly distinguishes the tool from 'leads_read', so an agent can identify its role without opening sibling schemas.

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 names the key alternative ('Different from leads_read (the CRM lead list)') and gives action-level selection guidance for list, get, timeline, and audit_log. It does not explicitly state when not to use the tool or compare it with other conversation-oriented siblings, but the action routing is clear.

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