Create Proposal

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

No annotations are provided, so the description carries the full burden, and it delivers well. It explicitly says 'Mutating: persists a proposal record,' clarifies that raising a proposal does not decide it, states that 'Design changes are never applied automatically,' and directs polling 'list_proposals' for the outcome. This is strong behavioral disclosure for a mutation tool.

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 description is front-loaded with the core purpose, then usage triggers, then the mutation warning, then the workflow context. Although it is longer than average, every sentence earns its place, and the second paragraph clarifies the decision workflow rather than padding.

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?

Given the tool complexity, missing annotations, and an output schema being present, the description is largely complete: it covers purpose, trigger conditions, side effects, decision workflow, and follow-up. A small gap is that the initially stated trigger conditions emphasize removal ('should lose a component' and 'removed by design') even though the schema supports broader design-change payloads, but the opening 'change of scope or design' mitigates this.

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 high at 83%, so the baseline is 3 even without parameter detail in the tool description. The description does not add parameter-level semantics, but the schema already explains 'kind', 'payload', 'evidence', 'model_id', and 'rationale'. The only undocumented parameter, 'server_version', is left to inference but is not a major burden.

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 opens with a specific verb and object ('Raise a proposal to change a model's scope or design') and immediately distinguishes itself from direct model editing. It even names the sibling tools it interacts with ('decide_proposal', 'list_proposals', 'get_design_leverage'), so an agent can tell exactly what this tool is and is not for.

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 explicit when-to-use guidance: 'Call this when the code or your analysis says the model should gain or lose a component, or that an attacker position or asset should be removed by design.' It also states a key exclusion ('do not edit the model directly for those changes') and delegates decision and outcome-checking to 'decide_proposal' and 'list_proposals'.

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