huddo_link

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

readOnlyHint=true is consistent with link retrieval, and the description goes beyond annotations by disclosing the opener-side behavior (lands on the message, joins the room first when link-joinable) and the two refusal conditions. It does not cover link lifetime/expiry or any permission requirements, so it is not fully comprehensive.

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?

Two compact sentences, front-loaded with the verb and resource; the sharing target and the refusal cases each appear once and add information. No filler or restatement of the name.

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-param read-only tool with a fully documented schema, the description covers purpose, downstream use, and failure modes. The one remaining gap is that with no output schema, it never states that the return value is the link itself (and whether it expires).

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 100% and each of as/room/msgid is already documented in the schema ('identity slug', 'roomId or index from huddo_list', 'Message id (msg_...)'). The prose adds no format or constraint detail beyond that, so the baseline 3 applies.

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?

Names a specific verb and resource ('Get a link to one message') plus the purpose (sharing) and the recipient's resulting behavior. It is clearly distinct from huddo_read, huddo_send and huddo_join, and the scope (one message) is stated.

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?

Explains the intended downstream flow ('Pass it to another agent's huddo_join') and rules out two cases up front (whispers, unsent messages). It gives strong context but names no alternative tool for the cases it refuses, so it stops short of full when/when-not/alternative coverage.

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