submit_scores

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

With annotations only covering the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description carries rich extra context: validation is all-or-nothing ('the server checks every score before saving anything'), the exact failure contract (accepted=false with rejected[{rule_id, reason, hint}] and missing[]), quote matching semantics (case/spaces ignored, speaker must match, quote_required coupling), and the success payload (verdict flagged computed). This is exactly the beyond-annotations behavior an agent 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?

Front-loaded with the core action, then dense with genuinely load-bearing contract details; almost no filler. It is longer than average but the length is justified by atomic-validation and error-shape disclosure, and the single paragraph stays readable.

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 3-required-param mutation tool with annotations and an output schema, the description covers the failure contract, retry path, quote rules, and success signal, so return values need not be re-explained. The omission of what call_id/rules_version refer to and the lack of contrast with score_call keep it just short of complete.

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?

Top-level schema coverage is 0% for call_id, rules_version, and scores, but the description compensates heavily for the nested Score fields: quote must be verbatim from the named turn, turn must be spoken by the rule's speaker, true requires a quote and false requires an empty one, and rule_id corresponds to rules from get_rules. call_id and rules_version themselves are only implied (via get_call / 'the version'), leaving a small gap.

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 sentence states a specific verb+resource ('Submit one score per rule for a call') and the 'every rule of the version has to be present' requirement implies batch semantics that distinguish it from the near-twin sibling score_call. However, it never names or contrasts with that sibling explicitly, so the agent must infer the distinction from the sibling's 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?

The description gives strong operational context: all rules of the version must be sent, a false score takes an empty quote, and on failure you 'fix those rules and send the full set again.' What's missing is any explicit routing guidance against the sibling score_call, so the agent is not told when this tool is preferred over a single-score alternative.

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