pipeline_did

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

The annotations already signal readOnlyHint=true, so no destructive behavior needs to be disclosed. The description adds useful behavioral context beyond annotations: it reveals this is a multi-stage orchestration tool that chains several diagnostics and returns a combined report plus a result_id. It does not disclose runtime/compute cost or that the pipeline may be heavier than a single diagnostic, but the read-only annotation lowers the burden.

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?

The description is only two sentences, with the workflow front-loaded before the use case. Every phrase earns its place: the stage chain, the output type, the result_id, and the decision rule. There is no filler or repetition of schema content.

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 complex 12-parameter pipeline, the high-level description is complete enough for an agent to know what the tool achieves and when to choose it. The output schema and rich per-parameter descriptions cover return values and optional behaviors like cohort dispatch and as_handle chaining. Nothing needed for correct selection or invocation is missing from the description itself.

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 92%, so the input schema fully documents the parameters. The tool description adds no parameter-level information, which is acceptable because the schema does the heavy lifting. It does, however, mention the concept of result_id and the result-report output at a conceptual level, but not in any detail.

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?

The description uses a specific verb phrase ('End-to-end DID workflow') and enumerates the exact pipeline stages: preflight, did/CS estimator, audit, honest-DID sensitivity, bacon decomposition, brief. It clearly states the output (one markdown report + primary result_id) and the intended trigger ('user pastes a DID dataset and asks 'is the effect real?''). This distinguishes it from single-step sibling tools such as audit or bacon_decomposition, even if it does not name a competing end-to-end alternative.

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?

There is an explicit when-to-use statement: 'Use this when the user pastes a DID dataset and asks 'is the effect real?''. This gives the agent a clear selection condition. However, it does not mention when not to use the tool, nor does it name alternatives such as auto_did or did_analysis when only a component diagnostic is needed.

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