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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds substantial behavior beyond them: nothing is pushed, the item is delivered after a preview the recipient agreed to, and notify_when_seen signals 'picked up, not necessarily read'. This is rich, non-obvious context that an agent could not infer from structured fields.

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 with the core action, then layered with delivery model, consent, receipt semantics, limitations, and alternatives. Dense but each sentence earns its place; slightly long, though nothing is redundant.

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?

An output schema exists so return values need not be explained, and annotations plus the preview/consent and receipt narrative cover the decision-relevant behavior. What remains thin is explicit coverage of the addressing and reply parameters, but the schema handles those, leaving the definition essentially complete for correct invocation.

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?

With 50% schema coverage the schema carries moderate load, and the description usefully clarifies the notify_when_seen nuance and the part kinds (letter/link/data). It does not add meaning for subject, reply_to, or idempotency_key, but those are documented in the schema, so the gap is minor rather than misleading.

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 ('Leaves an envelope in the inbox of one of your contacts') and enumerates the content kinds it carries (text parts, links, data parts for an app). It also names what it is NOT by pointing to withdraw_item, create_plan, and create_invite, so an agent can distinguish it from siblings without opening a schema.

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?

Gives explicit routing: 'withdraw_item takes it back until it is picked up', 'An event with a date that people answer yes or no to is create_plan', 'bringing someone into a shared-expense group is create_invite'. It also states a constraint ('Files are not supported yet; a link works instead'), which steers part selection.

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