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

Annotations declare mutation/destructive/idempotent, and the description adds substantial context beyond them: what makePrimary does, that unlinking the primary promotes another company, the stale_revision failure mode, and that an idempotencyKey retry returns the first result. The untrusted-content warning is a bonus safety note.

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?

Front-loads the purpose, then layers requirements, edge-case behavior, and safety note. Dense but each sentence earns its place. The untrusted-content line is properly segregated rather than mixed into the mechanism description.

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 no output schema, the description covers the prerequisites, the two action modes, primary-company side effects, the stale_revision return signal, and idempotent retry semantics. Nothing an agent needs to call it correctly appears missing.

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 only 14% schema description coverage, the description must carry the load and largely does: it explains action semantics, makePrimary, expectedUpdatedAt (source and stale_revision consequence), and idempotencyKey behavior. Only id/companyId (obvious UUIDs) and workspaceId (documented in schema) lack added meaning.

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+resource: 'Links a person (contact) to a company, or removes that link'. This clearly distinguishes the write operation from the read sibling get_contact_accounts, though no sibling is named explicitly. Clear and unambiguous 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?

Provides prerequisite ('you need access to both records') and routes the agent to get_record to obtain expectedUpdatedAt. Explains the action-dependent branch (link vs unlink, makePrimary behavior). No explicit when-not-to-use, but context is clear.

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