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

Annotations already declare mutating, non-idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds genuinely non-obvious context: the token is private material and must travel in the JSON body, never in a URL or routine summary. It does not say what state changes on success or what happens if the token is already consumed/expired, which keeps it off a 5.

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 sentences, zero waste, with the action and its ownership scope front-loaded before the token-handling constraint. Nothing is repeated from the title or schema.

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?

Single-parameter tool, no output schema, and annotations carry the mutability profile, so the description need not explain return values. It covers what the agent must get right — whose invitation, and how to pass the secret — leaving no call-blocking ambiguity.

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% with a 64-hex pattern already documented, so the baseline is 3. The description goes beyond that by governing how the single parameter must be transmitted (JSON only, never a URL) and reinforcing its private nature, which is real usage-relevant semantics the schema cannot express.

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?

Specific verb (accept) + resource (Company invitation) with an explicit scope qualifier: the authenticated user's *own* emailed invitation. That scope distinguishes it from company_invite_member, company_resend_invitation and company_revoke_invitation without naming them, though a direct sibling callout would make it a 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?

The triggering condition is clear: the user has received an emailed invitation and holds a token for their own acceptance. It implicitly excludes acting on other people's invitations. It does not name alternatives (e.g. resend vs. revoke when the token is missing/expired), so a small gap remains.

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