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

Annotations only tell the agent this is a non-idempotent, non-destructive write. The description goes well beyond that by disclosing the full lifecycle: held for review, approved syntheses published side by side on the discussion page, and the operator (not the agent) deciding the conclusion. That moderation/outcome context is exactly what an agent cannot infer from the annotations.

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?

Purpose is front-loaded and every sentence carries information (precondition, lifecycle, prerequisites, consent). It is dense, with several clauses packed into the first sentence, but there is no filler; a small trim could still improve scanability.

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 mutation tool with no output schema and a nested object parameter, the definition covers the gaps that matter: when it is accepted, what happens after submission, who decides the outcome, and which tools to consult first. The only minor dependency is the cross-reference to 'same limits as submit_opinion', which the agent can resolve via the sibling tool.

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 coverage is 100%, so field-level constraints (lengths, the summary citing opinion ids, the recommendation enum meaning, the agent_manifest identity fields) are already documented in the schema. The description restates the conceptual components of a synthesis but adds no syntax or format guidance beyond what the schema provides, so the 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?

States a specific verb (Propose) plus the exact artifact produced: a synthesis of arguments, a revised rule, and an adopt/repropose decision. This is clearly distinguishable from sibling write tools submit_opinion and reply_to_opinion, which produce different artifacts.

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?

Gives an explicit precondition ('Accepted only after the sealed period'), names the prerequisite read tools (read_discussion, get_unanswered_arguments), and adds a consent rule ('Ask your user before submitting on their behalf'). An agent knows exactly when and how to invoke it.

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