company_intelligence_readiness

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

The description discloses that the tool is read-only ('Read-only.'), which is one behavioral trait. However, with no annotations provided, the description carries the full burden for disclosing side effects, required permissions, rate limits, or failure modes. It does not mention any of these. The cryptic references to 'chains', 'recorded books', and 'plans to add' are not explained behaviorally. Given the lack of annotations, this is insufficient transparency.

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, long, run-on sentence that packs multiple ideas into one continuous clause. It is not front-loaded with a clear statement of what the tool does; instead it begins with a complex prepositional phrase. It would benefit from being broken into shorter sentences or bullet points. The content is dense and hard to parse, making it less effective for an agent trying to quickly understand the tool.

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 7 parameters and no annotations, the description is incomplete. It does not explain how to use parameters like operation, engine, entity_ref, or bundle_json. It also leaves ambiguous the meaning of key terms ('chains', 'recorded books') and does not describe what the output (which has a schema) will look like. While the output schema exists, it is not shown, and the description does not reference it. The description does not provide enough context for an agent to correctly invoke the tool.

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?

The schema description coverage is 0%, so the description must compensate by explaining the parameter semantics. It only mentions payload_json, noting it 'takes an optional connectors_bound list'. It does not explain the other six parameters (now, engine, operation, entity_ref, bundle_json, project_id) at all. Operation has a default of 'build' but its meaning is never described. The description fails to provide meaning for the vast majority of parameters.

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 attempts to state a specific purpose: assessing readiness of intelligence documents, including whether they can be built now, what evidence they rely on, and what would unlock them. However, it is verbose and convoluted, and does not cleanly name a verb+resource like 'check readiness for each document'. It also does not explicitly distinguish from similar siblings like 'company_readiness' or 'company_intelligence_review', though the focus on evidence and blockers is somewhat unique. Overall, the purpose is discernible but not crisply stated.

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?

There is no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or scenarios where a different tool would be preferred. The description only describes the tool's functionality without any context about when it should be invoked.

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