read_research_question

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

With no annotations, the description carries full burden. It discloses an authority restriction and an unread-content caveat, but omits whether the call mutates state (recording consumption implies a write), what happens on a second call, or what is returned.

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 short sentences with no padding, so length is fine. But the front-loaded sentence opens with a conditional ('Only this originating launcher...') rather than stating the action, making the opening harder to parse than it needs to be.

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?

A three-parameter, unannotated, no-output-schema tool needs the description to cover inputs and effects. This one covers neither the parameters nor the mutation semantics, leaving the agent without enough to call it confidently.

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 0% across three parameters (id, sender, request) and the description explains none of them — not what 'id' identifies, not why 'sender' is optional, not what 'request' contains. The agent is left guessing at all three inputs.

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 says the tool 'record[s] actual consumption of its delivered research question,' which is a mutation, yet the tool name is read_research_question and a sibling is 'acknowledge' — an agent cannot tell whether this reads or records. The scope ('its delivered research question') is named, but the core action is genuinely ambiguous against the name.

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?

'Only this originating launcher may...' states an access precondition and 'Never acknowledge unread content' states a prohibition, but neither tells the agent when to pick this over siblings like acknowledge, answer_research_question, or message_status. The guidance is a constraint, not selection criteria.

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