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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, and destructiveHint=false. The description adds useful operational context by saying the data is 'saved' and consists of declarations/public HTML observations, and reiterates that it never fetches a page or starts work, clarifying that it reads persisted evidence rather than live pages.

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 core action and followed by a tightly scoped exclusion. There is no redundant phrasing and every sentence adds useful 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?

The tool has no output schema and three undocumented optional parameters, so the description needs to do more than state the general resource. It does not explain what a 'deployment declaration' or 'public HTML observation' contains, how results are scoped by workspace/document/deployment, or what an agent receives.

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?

There are three parameters with 0% schema description coverage, and the description provides no meaning for workspace, documentId, or deploymentId. It does not explain optionality, whether these are filters, or how the identifiers relate to the returned deployment evidence.

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 uses a specific verb and resource: reading saved deployment declarations and public HTML observations. It also distinguishes itself from mutating/fresh-fetch siblings by stating it never fetches a page or starts work, though it does not explicitly contrast with nearby tools like record_page_deployment or read_website_pages.

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 phrase 'Never fetches a page or starts work' gives an implicit when-not condition and suggests this tool is for reading existing evidence only. However, it does not explicitly say when to choose this over record_page_deployment, prepare_page_changes, or read_website_pages, nor does it explain how the optional identifiers select scope.

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