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

Beyond the annotations (readOnly/idempotent), the description discloses meaningful traits: inputs are processed transiently and not stored/logged, gpu:true nodes always delegate to browser, and it exports an AP2 artifact with execution_hash for provenance. It adds real behavioral context that the readOnlyHint alone does not convey.

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 text is bloated with template boilerplate, a repeated 'Deterministic OpenChainGraph compute node' phrase, an external URL, and a long FV-status hash string. The actual purpose is not front-loaded; infrastructure detail crowds out the substantive function.

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?

There is no output schema, and the description partially compensates by noting the exported AP2 artifact and execution_hash. But for a compute node taking a nested policy_parameters object, it never explains what the computation returns or what the correction semantics are, leaving a functional gap.

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 100%, so the schema already documents compute, parent_hashes, parent_tool_ids, and policy_parameters. The description's compute-mode explanation largely duplicates the schema field description, and it adds nothing about policy_parameters beyond the schema. Baseline 3 is appropriate.

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 leads by restating the name/title ('Record Index Correction: OpenChainGraph compute node') and then describes generic runtime mechanics (compute modes, AP2 artifact export) rather than what an 'index correction' actually computes. An agent cannot distinguish this from siblings like record_index_constituents or compute_index_weights, since no functional verb+resource is stated.

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 gives real guidance on the compute parameter's auto/server/browser behavior and a clear constraint ('Use synthetic or anonymised inputs only'). However, it offers no guidance on when to choose this tool over the many sibling record/compute nodes, so tool-selection guidance is missing.

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