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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. The description goes beyond them by disclosing that nothing is sent to the client, that the record is reversible ('can be edited or removed in the app'), and the auth need ('Cotlet API key with access to this app'). That is real added behavioral value, though it stops short of saying what happens on duplicates or validation failures.

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 first two sentences are largely redundant, restating the same idea ('New client or lead with contact details and a service address. Creates a client or a lead with a service address and optional contact details and notes.'). The remaining sentences are tight and front-loaded, but one sentence could be cut without loss.

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 mutation tool with annotations present and no output schema, the description covers the key agent-facing concerns: no external side effects, reversibility, and auth requirements. Nothing critical is missing, though duplicate handling and validation behavior are unaddressed.

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 all six parameters plus the client/lead enum are fully documented in the schema. The description only mirrors the fields ('service address and optional contact details and notes') without adding format or default guidance, so the baseline 3 is appropriate.

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 ('Creates a client or a lead with a service address and optional contact details and notes'), so an agent immediately knows this is a create operation for the CRM contact record. It does not name any sibling (e.g. get_client, search_clients, create_job) to draw boundaries, so it stays at 4 rather than 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?

Provides meaningful context for when it is safe to run ('It sends nothing to the client, so it runs without asking first'), but never states when to prefer this over alternatives or what prerequisite state must exist. Usage is implied rather than instructed, and no alternative tool is named.

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