daily_brief_start

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

With no annotations, the description carries the full burden and does so: async fire-and-return semantics, the job_id handle, polling cadence, terminal status values (done/error), the rejection mode when too many jobs are retained, and the process-global config lock that can refuse a call. That is far more than the name or schema conveys.

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 core async contract, then failure modes, then args — a sensible order with no filler. The prose is dense and slightly run-on in places (the timeout aside, the tag clause), but for a six-parameter tool with zero schema documentation the length is largely earned.

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?

Covers the full lifecycle an agent needs: invocation, returned job_id, polling target and cadence, terminal states, rejection handling, and the concurrency constraint. No output schema exists, yet the description still tells the agent what 'result' holds, so nothing material is missing.

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 0%, so the description must compensate, and it documents all six parameters with real semantics: tag AND/OR grouping with case-insensitivity, intersection behavior when combined with hostnames, default look-back of 18 hours, route_baseline threshold behavior, and config_path fallback. This is exactly the syntax detail the bare schema lacks.

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 ('Start a daily_brief in the background') and immediately gives the distinguishing behavior: it 'returns immediately with a job_id'. It explicitly contrasts itself with the sibling daily_brief by naming the condition (fleet too large for one synchronous call) that separates them.

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 explicit when-to-use ('for a fleet too large for one synchronous daily_brief', citing the ~60 s per-call timeout), names the follow-up tool and cadence ('Poll daily_brief_result(job_id) every few seconds'), and states the when-not constraint (config_path cannot be switched while a job runs).

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