codex-sessions

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety is covered. The description adds genuine context beyond them: results are metadata only (no message bodies) and the listing is scoped to threads this bridge created. It does not state default size or ordering, leaving a small gap.

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?

One sentence, front-loaded with the action and resource, with the qualifier and the downstream use case packed into parenthetical and trailing clauses. 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?

For a simple, fully annotated, closed-world read with no output schema, the description covers what is returned at a high level (metadata, threadId) and why it exists. Only the pagination/limit behavior an agent would need for large histories is unaddressed.

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?

The single 'limit' parameter has 0% schema description coverage, so the description carries the full burden and says nothing about it — no default page size, no mention of the 1-100 range, no ordering semantics. With low coverage and no compensating text, this is a clear gap.

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 ('List recent conversations created by this bridge'), scopes it to bridge-created threads, and immediately qualifies the payload as metadata-only. It also names the sibling it feeds (codex-reply), so an agent can distinguish it from codex and codex-status without opening any schema.

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 'to recover threadId for codex-reply' clause gives an explicit use case and routes the agent to the consuming sibling. There is no explicit exclusion (e.g., when to use codex-status instead), which keeps it short of a 5.

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