codex_research

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description adds genuinely new behavior: no automatic provider/model fallback, a serialized queue isolated from agy, and a job-handle return when the wait budget expires. It also discloses what evidence is retained and returned (exact model/effort, session, usage). It does not mention auth or rate-limit characteristics, though openWorldHint implies them.

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?

Four short sentences with no filler, leading with the core action before constraints and return behavior. The telegraphic style ("No automatic provider/model fallback") is dense but each clause carries a distinct operational fact.

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?

With no output schema, the description steps in to describe return values (model/effort, session, usage, retained job evidence) and the async job-handle path, which is what an agent most needs for a long-running, wait-budgeted call. Only the missing when-to-use routing versus the agy siblings keeps it below full marks.

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 80%, and the schema already documents cwd, model (SPILLWAY_CODEX_MODEL default, account-dependent availability), prompt bounds, and wait_ms job-handle semantics. The description adds only indirect meaning via the mention of returned model/effort and the no-fallback rule for the model parameter. This is the expected baseline-3 case where the schema does the heavy lifting.

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?

"Run read-only research through a dedicated headless Codex CLI" gives a specific verb (run research) and resource (Codex CLI backend), and "Separate serialized queue from agy" distinguishes it from the agy research sibling. It stops short of naming agy_delegate_research directly, so the differentiation is inferential rather than explicit.

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 description establishes context (dedicated headless CLI, isolated queue, no provider/model fallback), and the schema's prompt description constrains scope to "bounded read-only research" with "no file edits or delegation." However, it never states when an agent should pick this over agy_delegate_research or local_exec_and_triage, leaving the routing decision to inference from queue/failure-mode hints.

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