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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the 10 MB packed size limit, the fact that the change is not committed until submit_app is called, and the redirect to publish_app for multi-file cases.

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 short sentences, zero waste, with the primary action and its constraints ordered before the alternative-tool routing. Every clause earns its place.

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 mutating tool with no output schema, the description covers the size limit, the deferred-commit workflow, and the sibling alternative, and annotations cover safety. Minor gap: it does not say whether the replacement discards unsaved state or what error occurs on exceeding the size limit.

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%, so slug, html, and api_key are already documented, and the description adds only the implicit 10 MB limit on html. Baseline 3 is appropriate when the schema carries the parameter 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?

States a specific verb and resource ('Replace the HTML of a web app you own') with the scope constraint (ownership, 10 MB) front-loaded. It clearly distinguishes itself from sibling publish_app and submit_app by naming what it does not do.

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?

Explicit routing guidance: 'It does not submit; call submit_app afterwards' defines the follow-up step, and 'For several files or an icon use publish_app with the slug instead' names the alternative and the condition that selects it. Nothing is left to inference.

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