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

The description discloses meaningful behavioral context beyond the readOnlyHint and destructiveHint annotations: collaboration flags, invoice visibility rules, owner_is_member behavior, and what show returns. This gives an agent a realistic model of the tool's domain effects without contradicting the annotations.

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 description is information-dense but well-structured, front-loading the purpose before explaining domain rules and action-specific details. It is longer than average, but the added context about collaboration and invoice visibility earns its place for a domain with nested semantics.

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?

There is no output schema, so the description must carry return-value information. It explicitly states what show returns and implies list returns standard company records. Given the tool's moderate complexity and 7 parameters, the description is largely complete, though list output details are not fully spelled out.

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 the baseline is 3. The description adds value by explaining that client_id finds companies where the client is a member or owner, that company_id is required for show, and by clarifying which parameters apply to which action. This is helpful semantic context beyond the raw field descriptions.

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 opens with a specific verb and resource: "List or show client companies (client teams)." It distinguishes the two actions, list and show, and explains the core concept of a company grouping client accounts. This clearly separates it from the sibling company-write tool.

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 description provides concrete guidance on when to use each action: list for filtered queries including finding companies by client_id, show for retrieving owner and member details. It does not explicitly name company-write as the mutation alternative, but the readOnly annotation and sibling naming make the boundary clear.

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