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

Discloses non-obvious side effects the annotations can't express: reading a conversation marks it read and surfaces in that chat's Min AI, and opening a profile reveals to its owner that the agent looked. That is exactly the context an agent needs before calling. There is mild tension with readOnlyHint=true, since marking read/notifying is a state change, but the description frames the operation as a read and the disclosure is helpful rather than contradictory.

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 sentences, front-loaded with the core action, and every clause carries information (targets, side effects, protocol). The second sentence is dense and packs several distinct ideas, but nothing is filler.

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?

An output schema exists, so return values needn't be described, and annotations cover the safety profile; the description still supplies the side-effect and social-visibility context plus the sensitive-case protocol. Only the explicit relationship to sibling read tools is left implicit.

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 the baseline is 3, but the description adds a formatting requirement not present in the schema: appending '#told' for the profile case. That is real semantic value beyond the documented id patterns (conv:…, plan:…, hunch:…, profile:<handle>).

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 ('Open one result from search by its id') and enumerates exactly what the id can resolve to: conversation messages, full plan, hunch, or whole profile. It doesn't explicitly contrast itself with the underlying siblings (read_conversation, read_profile, get_plan), so an agent still infers the relationship rather than being told it.

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?

Adds a genuine conditional protocol for the sensitive case ('tell your person first, then fetch the id with #told on the end') and notes the tool mirrors the rules of the tools behind it. It never says when to use fetch instead of read_conversation/read_profile directly, so the selection guidance is implied rather than explicit.

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