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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it explains IsEnabled defaults to DISABLED, that mobile holds names not credentials, that VAPID keys and subscriptions live elsewhere, that MaxSendsPerTitlePerDay is the only broadcast ceiling the API quota cannot see, and quiet-hours semantics. Rich behavior beyond structured fields.

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?

The leading 'PARTIAL SAVE' clause is well front-loaded, but the body is a dense run-on of many concerns (night sends, 3am, VAPID, subscriptions) in one paragraph. Most sentences earn their place through real behavioral detail, but the piece is longer than needed and lower-signal lines dilute the structure.

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?

Given no output schema and a nested config object, the description covers the mutation, default-to-off behavior, credential handling, and what is not in scope (VAPID, subscriptions). It is largely complete for a save tool, though it omits the response/return behavior and any precedence with get_push.

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 100% and every nested field carries its own detailed description, so the schema does the heavy lifting. The description adds conceptual framing (partial save, master switch default, quiet hours locale) but little new per-parameter semantics. Baseline 3 is appropriate.

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 (save/write) and precisely scopes it: 'writes ONLY the Push field of TitlePublicConfigurationModel; all other v1/v2 fields stay untouched.' This is a specific verb+resource and distinguishes it from the many sibling save_* tools by naming the exact field and model touched.

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?

The 'PARTIAL SAVE' framing and the note that other fields stay untouched implies when to use it (targeted push config updates), and the pairing with get_push is implicit. But there is no explicit when-to-use vs the sibling save_* tools or declaration of prerequisites (e.g. must read first). Usage is inferred, not stated.

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