Run a Spec pipeline

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

Annotations only indicate readOnlyHint=false and destructiveHint=false. The description adds critical side-effect context: it 'Consumes credits,' ingests file_urls first, returns a RunEnvelope with run_kind that dictates the polling target, and instructs to poll every 5–10s until terminal status. This goes well beyond the structured annotations and fully discloses the asynchronous, credit-consuming behavior.

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 dense but well-organized with clear sections (intro, inputs, USE WHEN, NOT FOR, ARGS, RETURNS). Every sentence earns its place; the core purpose is front-loaded, and the rest is tightly packed without fluff. It's long but justified by the tool's complexity.

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 tool with 7 parameters, two input paths, and a non-trivial return/polling contract, the description is remarkably complete. It explains how to obtain spec_id (talonic_list_specs), how to handle new files via the upload flow, the exact return structure, and the polling logic. Nothing an agent needs to call it correctly 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?

While schema coverage is 100%, the description adds meaningful semantics beyond the schema: it emphasizes 'exactly one of document_ids or file_urls,' spells out the limits (1–500 and 1–20), and clarifies that batch_id and metadata are only valid with file_urls. It also explains pipeline_mode ('new' vs 'append' to existing pipeline). This adds real value over the schema alone.

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 opens with a clear verb+resource: 'Run a Spec — the customer's configured pipeline — over documents, in one call.' It explicitly differentiates from siblings by naming what it is NOT for (talonic_extract, talonic_get_run, talonic_get_run_results) and clarifies the two input modes. An agent can immediately grasp the tool's role and scope.

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?

It provides a dedicated 'USE WHEN' section with concrete user intents (e.g., 'run the invoice pipeline on these documents') and a 'NOT FOR' list that names alternatives. It also gives conditional guidance on choosing document_ids (with the prerequisite upload flow) vs file_urls, and explains the polling flow after the call. This is explicit and actionable.

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