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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety profile is covered; the description's "set or update" wording is consistent with idempotent upsert semantics. However, it never states whether omitted categories are cleared, merged, or preserved — the most consequential behavioral question for a key-value preference map — nor whether the call returns the resulting preferences.

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 sentences, front-loaded with the verb and resource, followed by what is controlled and then scope routing. The enumerated category list partially duplicates the preferences schema description, which is the only redundancy.

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?

For a 4-parameter mutation tool with full schema coverage, annotations and no output schema, the definition covers purpose, controllable fields and scope selection. The merge-versus-replace semantics are the one omission an agent might need before calling it.

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 100%, so per the baseline the schema already documents scope, context, preferences and repository_id. The description restates the same category keys and notes custom_focus is optional/string-or-null, adding little beyond structured data.

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+resource ("Set or update AI code-review preferences") and explains exactly what the preferences govern, including the full category list and the global/repo scope model. An agent can distinguish this write tool from the read-side get_review_preferences sibling without opening a schema.

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?

Explicitly routes usage by scope: 'global' for everywhere-applicable defaults, 'repo' with repository_id for per-repo overrides. It does not mention the read counterpart (get_review_preferences) or say when not to override, but the branching guidance is concrete.

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