company_explain

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

No annotations are provided, so the description carries the burden. 'Read-only' is disclosed, which is useful. The description also explains what the output covers (transitions, receipts, evidence references, sources), which adds behavioral context beyond the schema. However, it doesn't describe any limits, format details, or what happens if the field cannot be explained.

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 and front-loaded: 'Explain a number' immediately states the action, then enumerates the trace components, and closes with 'JSON. Read-only.' It is efficient and well-structured for an agent to scan. One could argue for a 5, but it omits any parameter hints that could be earned in the same space.

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?

There is an output schema, so return values may be covered, but the input side is severely underdocumented. With 5 required parameters and 0% schema coverage, an agent cannot reliably construct a call. The description names the domain but does not specify how to obtain or format bundle_json, entity_ref, engine, or field values, nor how they relate to one another.

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%, and parameters are bare names with no descriptions: project_id, bundle_json, engine, entity_ref, field. The description mentions 'a persisted engine state's ledger field' which gives a hint about 'field' and possibly 'entity_ref'/'engine', but it doesn't explain what bundle_json is, what project_id refers to, or how they connect. With 0% coverage and 5 required params, the description fails to compensate.

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 says 'Explain a number: every transition, receipt, evidence reference, and source behind a persisted engine state's ledger field.' This is a specific verb ('explain'), a specific resource ('a persisted engine state's ledger field'), and names the scope of the explanation. It is clear enough to distinguish from siblings like company_revenue or workspace_trace, though it doesn't explicitly contrast with a near sibling.

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 guidance on when to use this tool versus alternatives. It doesn't state a selection condition, prerequisites, or when not to use it. The context signals (sibling tools like workspace_trace, company_brief, list_engine_states) suggest there could be overlapping trace/explain tools, but no differentiation is provided.

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