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

Beyond the annotations it discloses exactly what is mutated (sentAt, sendCount, an activity row, the render flagged sent), the default timestamp, tolerance for missing tags, and the specific failure mode ('locked email ... forbidden with details.code needs_person and details.resolveUrl'). It also flags untrusted content in results, which annotations cannot convey.

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?

The core purpose is front-loaded in the first sentence, followed by mutation effects, idempotency, return shape, and error case in a logical order. It is dense with clauses, and the closing untrusted-content sentence is boilerplate that could be trimmed, but no sentence is wasted.

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 3-parameter mutation with full schema coverage and annotations, the description covers trigger, side effects, timestamp default, idempotent path, return values (render plus sentAt/sentVia/sendCount), and the locked-email error with a resolution URL. Nothing an agent needs to call this correctly 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 defaults and enums are already documented; the description reinforces them ('sentAt is now unless given', agent_gmail as 'the default for this connection') and explains why a record can be written with missing tags. It adds interpretive value but little new parameter detail beyond the schema.

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 ('records that a rendered email went out') and immediately scopes it to emails sent outside LinkDrop ('through the agent's own mail tool ... or by hand'), which implicitly separates it from lnkdrp_send_email and other delivery tools. An agent can tell what this does and what it does not do without opening the 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?

It gives a clear trigger ('records that a rendered email went out some other way') and names the two channels (agent_gmail, manual), plus the idempotent case (already marked sent → returns stored state, changes nothing). It never explicitly says 'do not use this to send; use lnkdrp_send_email instead', so the negative case is left for inference.

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