find_clones

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

With no annotations provided, the description carries the full burden and does well: it discloses the ROI sorting formula, the unrefined-vs-refined semantics, the cap/clamping behavior, the completeness provenance block, and input validation ([0.5,1.0], out-of-range rejection). This is rich behavioral disclosure for a search tool; only missing details like auth or error behavior, which are less critical here.

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 a dense paragraph of about 70 words with zero fluff — every sentence earns its place (sorting, provenance, validation, cap behavior). It's front-loaded with the primary purpose. It could benefit from structural separation of the parameter constraints, but the information density is high and well-ordered.

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 tool with 4 well-documented params (100% schema coverage) and no annotations, the description covers the key behavioral gaps: return semantics without an output schema (ROI sort, provenance block, refine budget field). It's reasonably complete for a search tool that requires no parameters and has no output schema — the main omission is explicit differentiation from clones_for_symbol.

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 the schema already fully documents all four parameters (limit cap, worktree fallback behavior, min_copies default, min_similarity range). The description mostly restates this (limit clamped at 50, min_similarity range/default) while adding only the ROI context and the completeness.refine_budget_clamped field. That's marginal added value over the schema, matching the baseline 3.

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 clearly states the tool returns ranked candidate clone classes sorted by ROI, with a completeness provenance block. It's a specific verb+resource (return/find clone classes) with quantifiable scope. It distinguishes implicitly from the sibling clones_for_symbol (global vs per-symbol) but does not name the distinction explicitly, so it falls short of a 5.

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 substantial procedural context: the limit cap at 50, the refine budget behavior, and the min_similarity range enforcement. However, it provides no explicit when-to-use vs alternatives guidance, no exclusions, and never contrasts with the obvious sibling clones_for_symbol — so the tool-selection guidance is missing.

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