topos_preference_walk

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'Pure and read-only (lattice math only; no files, no scoring),' which reinforces and expands the safety profile by explicitly ruling out file operations and scoring. This is useful context beyond the annotations. It also clarifies the effect of the 'current' parameter (truncates the walk to steps strictly above it), which helps predict behavior.

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 compact—three sentences that efficiently cover purpose, usage context, and output structure. It front-loads the core action in the first sentence, is free of filler, and every clause adds value. The structure is well organized for quick parsing by an agent.

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?

While there is no output schema, the description enumerates the result fields (walk, next_step, progress, aspirational_target/fallback_target, induced_order), which covers return-value essentials. The input schema is rich, including detailed enum definitions for LatticeElement. For a read-only lattice-math operation with one required parameter, this is sufficiently complete. It could be slightly richer on what 'relaxation walk' implies, but the existing context is strong.

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%, so the schema already documents all three parameters (ranking, target, current) with clear descriptions. The tool description itself adds limited parameter-specific detail; it only mentions 'steps from target down to just above current' in the output, which indirectly references the 'current' parameter. Since the schema handles parameter semantics well, the baseline of 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?

The description opens with a specific action and resource: 'Turn a generator ranking into a preference-ordered relaxation walk.' This clearly distinguishes it from siblings like topos_evaluate_code or topos_compare_files, which are evaluation/comparison tools. It also names the concrete output type (PreferenceWalkResult) and its key components.

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 explicitly states when to use the tool: 'Call after an evaluation to pick the next verdict to aim for, or to relax the goal gracefully under a token/time budget.' This gives clear context. It does not explicitly mention alternatives or when-not-to-use, so it falls short of a 5, but the usage guidance is strong.

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