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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: the owner-approval prerequisite, the immutability of locked rules, and the concurrency requirement that existing entries need expectedRevision. It does not explain what a write actually destroys or overwrites.

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?

Four front-loaded sentences, each doing distinct work: purpose, locking, concurrency, idempotency. No filler, though the density is high for a compact paragraph.

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 the write semantics, approval gate, and idempotency are covered. However, for a 7-parameter mutation, the meaning of the status enum values and the remaining parameters is unexplained, leaving gaps an agent must resolve from the schema alone.

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, yet it only clarifies one of seven parameters (expectedRevision is required for existing entries). The status enum, programId, title, content, tags, and revisionReason 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 verb and resource: 'Save a fact the curriculum must not contradict,' which is more informative than the bare name 'record_noncontradiction_rule.' It implies a distinction from revise_approved_fact (locked rules until owner revises) but never names that sibling explicitly.

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?

Provides a clear gating condition ('only after the owner approves it') and a state rule ('Locked rules stay locked until the owner revises them'). It stops short of explicitly naming revise_approved_fact as the alternative when a locked rule must change, so routing to the sibling is only implied.

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