mark_read

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the exact state change (UNREAD removed from labels) and spells out the success payload with a concrete example, so the agent knows what comes back. It does not say what happens if the message is already read, if the ID is invalid, or what permissions are required, which are the remaining behavioral gaps.

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?

Front-loaded one-line summary followed by labeled Required / Returns / Workflow sections, which is easy to scan and appropriately short. Minor waste: the UNREAD removal is stated twice, and the return example has an unbalanced brace that slightly muddies the payload shape.

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 one-parameter mutation with no output schema, the description covers purpose, parameter source, return shape, and workflow context, which is close to what an agent needs. The gaps are edge-case behavior (already-read messages, invalid IDs) and the missing pointer to the bulk equivalent, neither of which blocks a correct call.

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 0%, so the description must compensate for the single parameter, and it does: it names the type and, more usefully, states provenance ('Gmail message ID from list_emails'), telling the agent where to obtain a valid value. It stops short of format details (opaque ID vs. numeric) or error behavior for bad IDs.

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 ('Mark an email as read') and immediately clarifies the underlying effect ('removes the UNREAD label'), so the agent knows this is a label mutation, not a status flag in some other system. It implicitly distinguishes itself from bulk siblings by saying 'an email', but never names mark_emails_read, so the singular/plural distinction is left to the name alone.

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 workflow note gives a concrete when-to-use case ('after reading an important email to clear the unread indicator'), which is more than most definitions offer. However, there is no when-not guidance and no routing to the obvious sibling mark_emails_read for batch operations, which is the most likely selection error an agent could make here.

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