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

Adds real behavior beyond the readOnly/idempotent annotations: deterministic, free, no model call, candidate sources returned cheapest first, plan_hash used for verification and approvals, and page labels are untrusted content to be treated as data. The untrusted-content and cost profile are exactly the kind of context annotations cannot convey.

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-loads the core transformation, then the return shape, then operational traits and the injection warning. Dense but every clause carries information; only the run-on enumeration of returned fields is slightly heavy.

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?

With no output schema, the description does supply the return shape, which is essential. However, for a tool with a nested target object and a plan_hash whose downstream consumers (approvals, verification) are only gestured at, an agent still lacks detail on target semantics and the unmapped entry structure.

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 80%, so the schema already documents goal, context_refs and page_schema_id. The description adds only that page_schema is optional and sourced from alterlab_task_schema; target and its url/entity/none enum are left entirely to the schema.

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 transformation: turn a goal (plus optional page_schema) into required facts with fact_key, kind, required flag, candidate sources, must_be_user_authored and risk_class_hint. It also names the sibling that feeds it (alterlab_task_schema), so an agent can place it precisely in the workflow.

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?

Implies sequencing ('optionally the page's schema from alterlab_task_schema') and tells the agent to classify unmapped questions with its own model, which is a usage instruction. But it never states when to call this versus alterlab_facts or alterlab_task_schema directly, and gives no exclusions.

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