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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, lowering the bar. The description adds real value beyond them: the 'WRITE:' prefix, the side-effect disclaimer ('does not send anything to the contact'), and the non-obvious conditional field requirements that differ from the schema's single required 'type'.

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?

Three short sentences with the operation mode front-loaded ('WRITE:'), followed by side-effect clarification and then the validation rules. No filler and no repetition of schema-only details.

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 14-parameter mutation with no output schema, the description covers the critical decision points: what it creates, that it has no outreach side effect, and the type-dependent required fields. It omits what the tool returns (e.g., the new contact's ID) and how duplicate conflicts are surfaced, which an agent would still need to discover empirically.

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 description coverage is only 29% across 14 parameters, so the description must compensate. It correctly fills the most consequential gap by explaining the conditional requirements per type ('Person needs first_name and last_name; Company needs name'), which the schema only hints at via scattered per-field notes. Remaining address/contact fields are left undocumented but are largely self-explanatory.

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 ('create a new contact in Lawcus') plus a scope qualifier ('a person or a company'), which immediately separates it from lawcus_get_contact and lawcus_list_contacts. An agent knows exactly what this tool produces without opening the 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?

Explicitly routes the agent to lawcus_list_contacts first to avoid duplicates, which is a concrete precondition rather than vague advice. It does not state when not to use it (e.g., updating an existing contact), so it stops short of full when/when-not coverage.

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