send_message_to_thread

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

With annotations declaring readOnlyHint=false and idempotentHint=false, the description adds meaningful behavioral detail beyond them: the message is visible to the recipient, the sender's thread ID is embedded so the recipient can reply, modelSelection alters the model, and a validation rule exists ('T3 can reject changing the provider of an already-bound thread'). Only the non-idempotent/retry implications are left unstated.

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 compact sentences, front-loaded with the core action and its state effects, then parameters, then the rejection rule. No filler, though the phrasing is dense enough that a sentence on commandId would have been a better use of space than some of the modelSelection detail.

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 5-parameter mutating tool with a nested object and no output schema, the description covers the main action and one failure mode, but leaves commandId unexplained and says nothing about what happens to a queued vs. started thread or how errors surface. Adequate but with clear gaps.

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 20%, so the description must compensate; it does explain modelSelection's effect and one provider constraint, but threadId, message, and commandId receive no semantic elaboration at all. 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?

The description states a specific verb and resource ('Send a visible follow-up to a peer thread in this project') and clarifies the effect on thread state (starting, queuing, reviving settled threads). It is clearly distinguishable from create_thread or read_thread, though it never names a sibling explicitly.

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 implies usage context by describing the scenarios that motivate a send (starting/queuing work, reviving settled threads), but it gives no explicit when-to-use vs. when-not guidance and no alternatives among the sibling tools (e.g., create_thread vs. send_message_to_thread).

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