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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it enumerates the state machine, states what `result` contains per provider, and warns that GitHub/Linear connections grant no Agent access until a separate select call. That is exactly the kind of context annotations cannot carry.

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 purpose, then state semantics, then remediation, which is a sensible order. The long parenthetical inventory of per-provider result fields is dense but each item is decision-relevant, so it earns its place despite length.

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?

One required parameter, an output schema, full annotations, and a description that covers states, result contents, downstream calls and failure recovery. An agent has everything needed to call it and act on the answer without opening another tool.

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% and the single attempt_id parameter is already documented as originating from provider_connect_handoff, so the description adds little beyond the actor-scoping note. Baseline 3 applies when the schema does the work.

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 and resource ("Reads one connection attempt") and names the originating sibling (provider_connect_handoff) plus the actor-scoping constraint. It is clear about what is returned, but only implicitly differentiates itself from provider_status/connection_context, which also surface connection state.

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?

Tells the agent how to interpret each terminal and in-flight state, and routes it: pending/authorizing/choosing means keep waiting, cancelled/expired/failed means re-issue a link, and GitHub/Linear resources require provider_resources_read before selection. It stops short of explicitly stating when to prefer this over provider_status on the sibling list, so not a 5.

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