submit_portal_recourse

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

No annotations are supplied, so the description carries the full behavioral burden for a mutating, legally significant action (Art. 22 human intervention). It never states whether an override is reversible, whether the recourse is logged/auditable, whether actor_role must be consistent with the chosen action, or what state changes result. The only added signal is that the override is performed by a human, which is useful but far short of what an unannotated mutation tool needs.

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?

A single front-loaded sentence that names the resource first and then the actionable cases; there is no filler. It is slightly compressed at the cost of precision (one enum action omitted), but structurally clean.

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?

The schema is rich (six parameters, three enums, 100% description coverage) and no output schema exists, so the description need not explain return values. Still, for a six-parameter mutation with no annotations and legal stakes, the definition leaves open who is authorized, what happens after submission, and whether the call can be undone — gaps an agent would want closed before invoking it.

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% and every parameter is documented inline, including the conditional requirement that override_verdict is needed for OVERRIDE_VERDICT. The description merely restates the action categories already embedded in the enum and adds no format, constraint, or cross-parameter semantics beyond the schema, so the baseline of 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?

States a specific verb+resource ('Actionner un recours sur le portail') and enumerates three of the recourse scenarios, so an agent knows this is a human-override/appeal submission tool rather than a read or execution tool. However, the description lists only three scenarios while the enum has four actions (EXECUTIVE_SIGN_OFF is never mentioned), and it draws no boundary against related siblings such as execute_procurement_intent or get_execution_audit_trail.

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?

Usage is implied by the enumeration of the three recourse cases (override verdict, flag ambiguity, Art. 22 clarification request), which hints at when the tool applies. There is no explicit mapping of scenario to the action enum, no statement of prerequisites (e.g. an existing contract_id from execute_procurement_intent), and no guidance on when not to use it or which sibling to prefer instead.

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