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

Annotations already cover the safety profile (non-readOnly, idempotent, non-destructive), so the description's job is to add what they cannot. 'Only ... explicitly reviewed' adds a real constraint: the committed decision must match the preview, the agent cannot substitute its own. It omits what happens on a hash/precondition mismatch, which is the key failure mode for a binding tool.

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?

One sentence, front-loaded with the core constraint and free of filler. Its brevity is efficient rather than padded, though it tips into under-specification for a nested-object mutation.

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?

A non-readOnly, nested-schema bind operation with 0% parameter documentation and no output schema needs the description to carry the preview-to-bind contract: where the hashes come from, that mismatches are rejected, and what 'decision' and 'comment' are for. One sentence does not cover that.

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% across 6 parameters including a nested 'binding' object with five required sub-fields (preview_hash, approved_action_key, approved_input_hash, approved_idempotency_key, resource_version_precondition). The description explains none of these — no meaning for idempotency_key, comment, decision, or any binding field — so the agent must infer the entire commit protocol from bare property names and minLength constraints.

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: 'Record ... the approval decision'. The phrase 'explicitly reviewed in preview' signals the bind-after-preview pattern that distinguishes it from yardstick_offers_approval_preview and yardstick_offers_approval_review, though it never names those siblings outright.

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 the prerequisite (a preview must have been reviewed) but does not state it as a rule, nor does it name the preview tool or say what to do when no preview exists. Usage is inferable rather than directed.

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