Run ATR

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the mutating-but-non-destructive profile is covered structurally. The description adds real behavioral context beyond that: recognizing all pages consumes credits per page, a cost consequence the annotations do not convey. It does not, however, describe job/async behavior or result retrieval.

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?

Two tight sentences with the primary action front-loaded and the credit consequence appended, with no filler or redundancy.

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?

As a credit-consuming mutation with no output schema and no docs on how modelId interacts with ATR, the description leaves gaps: it does not explain model selection, whether the run is synchronous, or how to track the resulting job. Annotations cover the safety profile and the credit note covers cost, so it is minimally viable but not fully self-sufficient.

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 coverage is 100%, so the baseline is 3, and the four parameters (collId, docId, pageNr, modelId) are all documented in the schema. The description goes beyond that by defining what happens when pageNr is omitted, a default-behavior detail the schema's 'Page number' text does not capture. It says nothing extra about modelId selection, but the pageNr clarification lifts it above baseline.

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 (Run) plus resource (Automatic Text Recognition) and scope (one page or a whole document), so the core action is clear. However, it never distinguishes itself from close siblings like transkribus_recog_run_ocr or transkribus_recog_run_trhtr, leaving the agent to infer the difference from the name alone.

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?

Provides a useful conditional ('Omitting pageNr recognizes every page'), which is genuine usage guidance. But it offers no when-to-use versus alternatives, no prerequisites, and no routing among the several sibling recognition tools.

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