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

Annotations cover safety (readOnly, idempotent, non-destructive), and the description goes well beyond them: scoring method (jaccard with hub penalty), exclusion of wanted shared contracts, per-seam evidence and confidence, and the advisory 'proposes, does not decide' framing. It even cites a backtest bench with a lift figure, which tells the agent how much to trust output.

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?

Front-loaded with the core definition before the scoring and parameter details, so the agent gets the gist in the first sentence. There is some redundancy — the risk-axis contrast and 'a seam is not a bug' point are restated — and capitalized emphasis plus a quoted example make it denser than necessary, but nearly every sentence adds information.

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 5-parameter read-only analysis tool with an output schema, the description supplies purpose, method, trust signal, and most parameter guidance; return-value shape is legitimately left to the output schema. An agent can decide to call it and how to tune it from this text alone.

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?

With 0% schema description coverage, the description must carry parameter meaning and largely does: it enumerates scope values (actionable default | all | expected), explains min_jaccard filters weaker seams, and defines zone as path prefix or words. Gaps remain: `limit` (default 30) and `repo_url` are never described, and 'actionable' vs 'expected' is not disambiguated.

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+resource (architecture seams of an imported repository) and defines the concept precisely: a source of truth split across module boundaries, detected from co-change history. It also explicitly contrasts itself with the risk axis and names hokmah_risky_code's domain ('where is the code fragile?'), so an agent can distinguish it from siblings without opening the schema.

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 clear selection context by framing this as a distinct axis from risk and explaining that seams are proposals, not bugs, plus how to narrow results via scope/min_jaccard/zone. It stops short of an explicit 'use this when X, use hokmah_risky_code when Y' routing statement and does not define what 'expected' scope returns.

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