analyze

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

All annotations are false, so the description carries the full burden. It discloses key behaviors: re-indexing if the tree changed, running tests in an isolated copy, being bounded by budget_seconds/budget_calls, and returning a specific structure. It also notes that needs_clarification is a normal result. This goes well beyond the annotation defaults and gives the agent a clear picture of side effects and constraints.

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 single dense paragraph with multiple clauses and semicolons. It is front-loaded with the purpose, but the overall structure is a wall of text that is hard to parse. It could be broken into logical sections (purpose, behavior, returns, constraints). It is not concise; it packs a lot of information but sacrifices readability.

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 complexity (6 parameters, no output schema), the description is remarkably complete. It explains the return values (snapshot, understood_as, per-sub-question verdicts, claims, unknowns, passages), behaviors (re-indexing, isolated test runs), constraints (budgets), and a normal outcome (needs_clarification). Nothing critical is missing for an agent to invoke it correctly.

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 baseline is 3. The description adds integration context (e.g., 'sub-questions (from the question, or a checked plan_json)' and 'run_tests / observe also run or trace the tests') that ties parameters together, but it does not add per-parameter detail beyond what the schema already provides. It adds marginal value but does not compensate for anything missing.

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 'Answer a question as claims with evidence' – a specific verb and resource. It distinguishes itself from sibling inspection tools (node_inspect, relation_trace) by being a comprehensive analysis tool that combines retrieval, test execution, and evidence synthesis. It is not a tautology and leaves no doubt about its core function.

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 rich context about how the tool works (sub-questions, plan_json, isolated test runs) and mentions that needs_clarification is a normal result, implying it handles ambiguous questions. However, it never explicitly states when to choose this tool over siblings, such as 'use this when you need evidence-backed answers' or 'for quick lookups use node_inspect instead.' The guidance is implied rather than explicit.

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