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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower, and the description still adds meaningful side-effect disclosure: opening a chat marks it read and surfaces it in 'its Min AI', and opening a profile is visible to that profile's owner. The unresolved tension is that these are real state changes and third-party visibility, which sits awkwardly with readOnlyHint/openWorldHint=false; the description does not explain 'Min AI' or exactly what the owner sees.

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 short sentences, front-loaded with the core action, and each sentence carries distinct information (action, chat side effect, profile side effect plus the #told rule). The trade-off is cryptic domain jargon ('Min AI', '#told') used without definition, which costs a little clarity without adding length.

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 one-parameter tool with full annotation coverage the description is close to sufficient, and it usefully covers side effects. But with no output schema, it never says what 'opening' returns (a conversation, a plan, a profile view?) or in what shape, and the '#told' mechanism is left unexplained for a rule that gates a socially sensitive action.

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 id parameter and its conv:/plan:/hunch:/profile:<handle> forms are already documented, giving a baseline of 3. The description adds genuine meaning beyond the schema by introducing the '#told' suffix convention that appears nowhere in the input schema, although it never explains how that suffix interacts with the 240-character id limit or the documented id format.

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?

"Open a search result by id" gives a specific verb (open) and resource (a search result) and makes clear the id is the input, which is more precise than the bare name 'fetch'. However, it never distinguishes itself from the many read-type siblings (read_chat, read_plan, read_profile, read_thread) that appear to cover overlapping resource types, so an agent cannot tell from the description alone when to use fetch instead of those.

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?

One conditional when-to instruction is given: before opening a profile that belongs to someone, tell your person first and append '#told'. That is useful but narrow; there is no guidance on when fetch should be chosen over read_chat, read_plan, or read_profile, and no statement about when not to use it.

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