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

Annotations already cover readOnly/destructive/openWorld, but the description adds real behavioral detail beyond them: the HTML is sanitized, images are rewritten, and no plain-text body is included. This tells an agent what the payload actually contains.

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?

A single tight sentence that front-loads the key fact (returns HTML) and immediately qualifies scope (sanitized, image-rewritten, no plain text). No waste.

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?

With no output schema, the description carries the return-value burden and does so well, stating the HTML-only nature and the sanitization/rewriting transformations. For a simple two-param read tool with readOnly annotations, this is nearly complete.

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 both parameters (domain, emailId) are already documented in the schema, including that emailId comes from get_store_emails. The description adds no parameter meaning beyond that, so baseline 3 applies.

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: returns one captured email's sanitized, image-rewritten HTML. It differentiates itself from get_store_email by noting it is a companion that emits HTML and omits the plain-text body. The distinction is clear at a high level, though it doesn't spell out what get_store_email itself returns.

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 'used by the email-viewer widget' and 'Internal companion to get_store_email' implies the rendering context in which to use it, but there is no explicit when-to-use/when-not-to-use guidance or named alternative condition. Usage is only implied.

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