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

Annotations already declare readOnly/idempotent/non-destructive, so the description is not carrying the safety burden. It does add genuinely non-obvious behavior: the content is re-verified against its fingerprint on every read. The gap is that it doesn't say what happens when verification fails (error vs. warning).

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?

Two short sentences, front-loaded with the action, zero filler. Every clause contributes information.

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-value explanation is not required; the brief mention of title and client is a bonus. The remaining incompleteness is the fingerprint-mismatch behavior and the id/content_hash requirement rule.

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 0%, so the description must compensate. It usefully explains that content_hash is the fingerprint (an alternative key to id), which the bare schema does not. However, both params default to null and it never states whether at least one is required or what happens if neither is supplied.

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 ('read a frozen brief back') and names the two lookup keys. It clearly differs from grill_list/grill_get in shape, though it never explicitly contrasts itself with those siblings.

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?

Usage is implied — use this to retrieve an already-frozen brief — but there is no explicit guidance on when to prefer it over grill_get or grill_list, nor any stated precondition (e.g. that the brief must already be frozen).

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