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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description goes further by explaining compute routing ('auto' vs 'browser' delegation, gpu:true always delegating), transient non-retained processing of inputs, and emission of an AP2 artifact with execution_hash for provenance. This is real context beyond the annotations and does not contradict them; the only reservation is that much of it is node-generic boilerplate rather than specific to this check.

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 prose is heavily padded with infrastructure boilerplate ('OpenChainGraph compute node' restated twice), a raw FV-status SHA-256 URL, and repeated compute-mode wording that duplicates the schema. The actual regulatory substance is buried mid-paragraph and cut off mid-sentence, so the description is not front-loaded on what matters.

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 nested-policy compliance check with required keys (jurisdiction, retention_method, all_exposures_qrm_qualified, etc.) and no output schema, the description should explain the retention test itself (5% baseline, QRM exemption, valid methods, hedging/sale restriction). Instead the regulatory basis sentence is incomplete, and the output list is delegated to describe_tool, leaving the decision logic undocumented.

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 the policy_parameters sub-fields including the required-key list. The description adds no meaning beyond that (it does not explain jurisdiction values, retention_method options, or QRM semantics), 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 opening line names a specific verb+resource ('Securitization Risk Retention Check') and ties it to EU Securitisation Regulation 2017/2402 Art.6, which an agent can match to a retention-compliance task. However, the regulatory summary is literally truncated ('Art.6 and U.S.') and nothing distinguishes it from the many other regulatory-check siblings (e.g. check_mica_reserve_disclosure, check_genius_reserve_disclosure).

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 statement of when to use this tool, when not to, or which sibling (e.g. check_mica_reserve_disclosure, assess_* fit tools) covers an adjacent case. The only usage-adjacent content is the boilerplate compute-mode guidance and 'Use synthetic or anonymised inputs only', which constrains inputs rather than selection.

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