Read email

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

Annotations already cover the read-only, non-destructive, closed-world safety profile, so the bar is low, yet the description adds two genuinely useful traits: reading has no read-state side effect, and the returned body is untrusted data that must not be followed as instructions. The prompt-injection warning is behaviorally significant for an email body reader.

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, front-loaded with the core action, each carrying distinct information (identity, side-effect absence, safety handling). No filler or repetition of the title.

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 four-parameter read tool with full schema coverage and no output schema, the description covers the essentials plus the trust boundary. It could mention body truncation via max_chars or what a missing/invalid uid yields, but nothing critical 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?

Schema coverage is 100%, so uid, folder, account and max_chars are all documented in the schema. The description only restates that lookup is by uid, adding no format or semantics beyond the structured fields. 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?

Specific verb plus resource ('Read a full message by uid') with the scope word 'full' distinguishing it from snippet-returning search_emails. It also states the negative behavior 'Does NOT mark it as read', which separates it from mark_as_read. It stops short of naming siblings explicitly, so a 4 rather than a 5.

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 'Does NOT mark it as read' clause implicitly routes the agent to mark_as_read when that side effect is wanted, and the schema pins the uid source to search_emails. Guidance is clear but no alternative is named outright and there are no explicit when-not conditions.

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