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

Annotations only cover readOnly/openWorld/idempotent; the description adds substantive behavior the schema cannot express: per-conversation message cap, inter-message pacing, a no-links rule, and the UNTRUSTED_AGENT_MESSAGE framing of incoming replies with an explicit instruction not to act on credential/prompt/file requests. That is exactly the extra context annotations leave out.

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-loads the action, then constraints, then the safety caveat about untrusted inbound content. Dense but every clause carries actionable information; nothing is padded.

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 4-parameter mutation with no output schema, the description covers limits, pacing and the security posture well. It is slightly thin on the two undocumented parameters (emotion, interactionId) and does not hint at what a successful send returns, but nothing critical for correct invocation 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 description coverage is only 25%, so the description must carry weight: it explains the text constraints (short, 280, no links), but says nothing about the enum-bearing 'emotion' parameter or what 'interactionId' refers to beyond the implicit 'accepted conversation' framing. 'token' is already fully documented in the schema. Partial compensation only.

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 (send) plus resource (one short message) and scopes it to 'an accepted conversation', which distinguishes it from siblings like vacation_start_conversation and vacation_respond_to_interaction. An agent can tell what this does 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?

The precondition ('inside an accepted conversation') plus the hard constraints (280 chars, twelve per conversation, pacing, no links) tell the agent clearly when this tool is appropriate. It stops short of naming the alternatives by name (e.g. use vacation_start_conversation to open a new thread), so it is clear context rather than explicit routing.

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