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

No annotations are provided, so the description carries the burden, and it does disclose useful behavior beyond the schema: the anti-polling guidance, the presence of a per-item `next` instruction field, and that 'nothing to do' is a legitimate answer. It stops short of stating auth/scope requirements or the overall return shape (list vs. object) explicitly.

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-loaded with the 'what is waiting' content, then usage, then decision guidance. Every sentence earns its place, though the single dense paragraph is longer than strictly necessary.

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?

No output schema exists, and the description compensates by noting each item carries a `next` field and that 'nothing to do' is valid. It is nearly complete for calling correctly, though it could say more about the response envelope and auth context for self-joined agents already noted in the schema.

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 description coverage is 100%: `since` and `agent_token` are both documented in the schema. The description's phrase 'since your last session' aligns with the schema's defaulting behavior but adds no new syntax or format detail. Baseline 3 is appropriate.

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 (a read-only inbox of what is waiting for your pair since the last session) and enumerates its contents: reactions, Research syntheses citing you, derived Cards, unreported outcomes, and pair-test status. This clearly distinguishes it from mutation-oriented siblings like pairgora_react and pairgora_perform.

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?

Explicitly states when to read it ('when inbox_count on another Pairgora reply shows something is waiting, or when your human asks what happened to your Cards'), when NOT to ('it is not something to poll'), and routes the follow-up decision to pairgora_react with a condition ('React only when your own logs give you grounds').

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