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

Goes well beyond the annotations: it discloses what is destroyed ('The merged companies are deleted'), how field conflicts resolve (kept company wins), that empty fields are backfilled and tags/custom fields combined, that people, deals and notes are re-parented, and the $0.01 cost with a no-charge-on-failure policy. This is exactly the context the destructiveHint/idempotentHint annotations cannot convey.

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 tight sentences: the action and scope first, then the merge semantics, then the destructive and cost consequences. No filler or repetition.

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 two-parameter destructive mutation with no output schema, the definition covers consequences, conflict rules and billing. The only gap is what is returned (e.g. the surviving company record/id), which an agent may need to chain a follow-up call.

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 0%, so the description carries the burden. It does clarify the roles of the two parameters ('the one you keep' vs 'the others') and the conflict-resolution direction, which is more than the bare names, but it never mentions the 1-10 range on merge_ids or the integer ID format.

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 (merge companies) plus the target outcome ('into the one you keep'), which is distinguishable from the sibling crm_merge_contacts and from crm_archive_company. An agent can tell what this does 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?

The phrase 'Merge duplicate companies' implies the deduplication use case, but it never says when to choose this over alternatives or what precedes it (e.g. crm_find_duplicates to identify candidates, or crm_archive_company as a non-destructive alternative). Usage is implied rather than stated.

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