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

Annotations cover safety (non-readOnly, non-destructive, non-idempotent), and the description adds useful behavior beyond them: the header-vs-key precedence rule and the fact that accepting triggers a showdown via callout acceptance. It does not address repeatability or what happens on an already-used code.

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 compact sentences, front-loaded with the action and credential rules. The phrasing is slightly telegraphic in places but nothing is wasted.

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?

Auth paths and the guest restriction are covered, and there is no output schema to explain. However a state-changing acceptance tool omits what the agent gets back, what failure modes exist (expired/consumed code), and how it interacts with pit_accept_callout.

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 67%, with key and ref already described in-schema. The description restates the header/argument fallback for key but adds no detail about code or ref, so it does not meaningfully exceed the schema.

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 ('Accept code') and the credential types accepted. It implicitly distinguishes from pit_invite_create/pit_invite_cancel, though it never names those siblings explicitly.

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?

Gives one constraint ('Guests accept casual only') and notes that acceptance starts a showdown, but provides no explicit when-to-use rule or routing to alternatives such as pit_accept_callout, which covers a similar acceptance concept.

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