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

Annotations already establish a safe, idempotent read, and the description goes well beyond them: charges are provisional until settled, evidence is untrusted reference data, completion alerts live in Publinio, and background notifications depend on client scheduling. This is genuine behavioral context the structured fields do not 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-loaded with the purpose, then layered constraints and caveats in a tight block. Every sentence carries information — polling discipline, evidence tiers, charge provisionality, alert ownership — with no filler or restatement of the schema.

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 an output schema present, the description need not explain return shapes, and it correctly focuses on what the schema cannot convey: staged output by lifecycle state, polling etiquette, and charge/evidence caveats. An agent has everything needed to call this correctly and interpret the result.

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. It fully explains includeEvidence (false always omits, true explicitly loads current observations beyond the default) and 'one brand-scoped research run' implies the required brandId/runId pair, though neither is described in terms of format or provenance. Good compensation, with a small residual gap on the two required identifiers.

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?

Opens with a specific verb and resource — 'Read one brand-scoped research run' — and immediately scopes what is being read ('source progress and credit settlement'). This distinguishes it cleanly from list_research_runs, start_research, cancel_research and quote_research without needing the 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?

Gives explicit conditional behavior (lightweight progress while active, full evidence and cited brief once settledAt is present), states the includeEvidence=false vs true distinction, and adds a clear prohibition: 'never restart a run to check progress.' That is a when-not rule most definitions omit.

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