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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by defining the division of labor (tool supplies evidence, assistant detects contradictions) and restating the non-mutation guarantee for emphasis ('Does not save or approve anything').

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?

Three short sentences, front-loaded with what is retrieved, followed by the usage contract and the negative guarantee. Every sentence carries information, though the second and third sentences could be merged with no loss.

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?

An output schema exists, so return values need not be described, and annotations plus the description together give a complete behavioral picture. The remaining gap is parameter-level detail, which is minor for a small read tool whose arguments are largely self-explanatory.

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%, so the description carries the full burden, and it only implicitly touches one parameter via 'short proposed lesson or answer' (proposedText). Neither programId nor offset is explained, and no format, UUID, or pagination semantics are conveyed.

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 gives a specific verb (retrieve) and enumerates the exact resources it returns: locked promises, module outcomes, and non-contradiction rules. This is well above a tautology and separates it from mutation siblings like record_promise or revise_approved_fact, though it never names the read-side siblings (search_curriculum, get_curriculum_context) it most resembles.

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?

It states the triggering condition clearly ('so the assistant can compare them with a short proposed lesson or answer') and assigns responsibility ('the assistant must identify contradictions'). It does not, however, explicitly say when to prefer this over search_curriculum or get_curriculum_context, so the routing is implied rather than stated.

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