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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, so "WRITE" adds nothing the structured data didn't. The description omits meaningful behavioral context: duplicate-name handling, whether owner_id/tag_ids must pre-exist, and side effects of creating a company record — all relevant given destructiveHint=true.

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?

Two short fragments, front-loaded with the operation and then the endpoint; no filler or repetition. It is efficient, though the same brevity is what leaves the tool under-specified for a 14-parameter mutation.

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 create tool with 14 parameters, nested custom_fields, no output schema, and a destructive annotation, the description covers almost none of the context an agent needs — required-field emphasis, duplicate handling, or what the call returns. The structured fields carry the load, but the description leaves a clear gap.

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 14 parameters and 100% schema description coverage, the schema fully documents each field (name, web, email, custom_fields, etc.), so no description-side compensation is required. The description adds no parameter meaning at all, which lands at the baseline for high coverage.

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 gives a specific verb and resource ("create a company"), which cleanly separates it from siblings like create_person and create_deal. The "WRITE:" prefix reinforces the mutation intent. It stops short of anything beyond the bare operation, but the purpose is unambiguous.

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 on when to create a company versus updating an existing one (pipelinecrm_update_company), nor any precondition such as looking up duplicates first. The "WRITE" tag implies a mutating context but names no alternatives and sets no usage conditions.

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