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

The description discloses several behavioral traits beyond what annotations provide: invalid keys/values are reported and skipped, changes are not live until the next publish, and iOS/Android settings have post-publish limitations. Since annotations only give hints (readOnlyHint=false, destructiveHint=false) and do not cover these details, the description significantly enriches the agent's understanding of how the tool behaves.

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 description is long but every sentence adds necessary information: key list, validation behavior, timing, and post-publish alternatives. It is front-loaded with the core purpose and then dives into specifics. While dense, it is not redundant or fluffy, so the length is justified.

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 write operation with complex side effects, the description covers all necessary context: what fields can be updated, how invalid values are handled, when changes become effective, and what to do after publish. It also points to get_guides for further details on iOS/Android specifics. Nothing an agent needs to call this tool correctly is missing.

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?

The input schema provides no descriptions for the parameters (0% coverage), so the description carries the full burden. It explains the 'updates' object in detail, enumerating all valid keys (title, description, iconUrl, splashUrl, mobileAppId, enableSSR, flootAiDisallowed, iOS Info.plist keys, boolean keys) and their types, plus special handling (null to remove, booleans). This fully compensates for the schema's lack of semantic detail.

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?

The description clearly states 'Update project settings' and lists the specific keys, making the verb and resource unambiguous. It does not explicitly name a sibling tool to distinguish from, but the scope is specific enough that an agent could infer it is distinct from tools like create_project or list_projects.

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 description provides explicit guidance on when to use the tool and when not to: it states that changes take effect only after the next publish, and after the first iOS/Android publish, the user should edit files directly instead. It also names the alternative tools (write_file/edit_file and get_guides) and gives conditions, which is exactly the kind of operational guidance expected.

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