propose_belief

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

No annotations are provided, so the description carries the full burden. It does disclose meaningful behavior: the record lands as 'Proposed for human approval' and is 'staleness-checked against history from the moment it exists.' This adds real value. However, it does not state the return/response shape, failure behavior, or any side effects beyond the proposal status — a notable gap for a write operation with zero annotation coverage.

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?

Three dense sentences with the core purpose front-loaded, followed by format specs and the constraint. The format specifications are packed tightly and each sentence earns its place. Slightly heavy on the type-notation details, but nothing is wasted — appropriately concise for the information conveyed.

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 five parameters, no annotations, and no output schema, the description covers the critical input semantics and constraint well but leaves gaps: 'claim' and 'tier' are unexplained, the response/proposal-approval flow is only hinted at, and the 'staleness' mechanism is mentioned without elaboration. It is workable for a competent agent but not fully self-sufficient.

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 0%, so the description must compensate — and it largely does. It explains evidence format ('path:start-end', 1-based inclusive lines), paths ('repo-relative paths or globs'), symbols ('path:Name'), and the mutual-requirement constraint. This adds substantial meaning beyond the bare schema. However, the 'claim' and 'tier' parameters receive no explanation, which keeps this from a 5.

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 states a specific verb and resource ('Record an evidence-anchored belief about the code') and adds a distinguishing detail: the belief 'lands as Proposed for human approval'. This differentiates it from siblings like reaffirm_belief (which presumably updates an existing belief) and propose_changeset, but it does not explicitly name the sibling it is not, so a small inference gap remains.

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 no explicit when-to-use vs when-not-to guidance and names no alternative tool. While 'At least one of evidence/paths/symbols is required' clarifies a precondition, it never routes the agent to reaffirm_belief for updating existing beliefs or explains when proposal vs. direct record is appropriate. The contrast with reaffirm_belief is left entirely implicit.

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