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

Annotations only declare write/non-destructive/open-world; the description adds genuine context beyond them — the id is returned, network linking has downstream automation consequences, and "nothing is sent to the person" closes the obvious worry for a contact tool. It does not cover the fact that zero parameters are required, so an agent gets no guidance on the minimum viable payload.

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?

Four sentences, none wasted: purpose first, linking rule and its consequence second, dedup/alternative routing third, side-effect reassurance last. Parentheticals carry useful qualifiers without derailing the front-loaded main clause.

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 9-parameter mutation tool with no output schema, the description covers return value, side effects, linking semantics, and alternatives. The remaining gap is that every parameter is optional, so nothing states what a minimal valid call looks like or what happens with an empty payload.

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 100%, so the per-parameter baseline is 3; the description earns above that by explaining the coupling between accountId and username and the behavioral consequence of omitting them, which the schema only states as terse "Needs accountId" cross-references. It does not address workspaceId or idempotencyKey, but the schema handles those adequately.

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 ("Add a person to the CRM") with scope qualifiers — manual creation versus contacts auto-created by inbound writers. It also names the return value (created contact with its id) and explicitly distinguishes itself from update_contact, so an agent can separate it from siblings without opening a schema.

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?

Gives explicit routing: check list_contacts first to avoid duplicates, use update_contact to modify an existing contact, and pass both accountId and username to link to a network. The when-not (without both fields the contact is CRM-only and unreachable by network automations) is stated as a consequence, not left to inference.

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