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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: transient processing with no storage/logging/retention, the 'use synthetic or anonymised inputs only' constraint, and the deterministic hash-bearing AP2 export for chain provenance. What is missing is any note on failure modes or what a browser-delegation response looks like.

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 opening repeats itself ('OpenChainGraph compute node (compliance_control). Deterministic OpenChainGraph compute node.'), and the trailing FV-status URL plus verification caveat occupy space disproportionate to their selection value. The compute-mode explanation is useful, but the definition could be materially shorter without losing decision-relevant 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 4-parameter, no-output-schema compute node, the definition covers the execution model, input handling policy, provenance export, and pipeline position well enough for an agent to call it correctly. The main gap is the absence of any return-shape hint (server result vs browser delegation URL) now that compute:'browser' can change the response type.

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 enum values for 'compute', the parent_hashes/parent_tool_ids chaining semantics, and the policy_parameters pass-through are already documented in the schema. The description restates the compute-mode behavior but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 identifies the tool as a 'Mastercard Agentic Token Scope Builder' compute node but spends most of its words on the OpenChainGraph runtime mechanics rather than on what scope/artifact the tool actually produces. A specific verb+resource is present in the title, but the body does not sharpen it beyond that, so distinguishing it from the many other 'build_*' siblings requires inference.

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 no explicit when-to-use/when-not or named alternative, but the description does provide chaining context ('Consumes upstream artifacts from: art-22..., art-23...' and 'Output feeds: art-18..., ptg-01...') that implies when this node fits in a pipeline. That is meaningful implied guidance rather than none, though the agent must still infer the trigger conditions.

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