access.requestPermission

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety frame is partly given. The description adds genuinely useful behavior: the origin comes from the transport rather than arguments, Undo is none, Completion is completed, and the possible errors (internalError, invalidParams) are enumerated. What it omits is the interaction model — whether this blocks or surfaces a user prompt, and what a success response contains.

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?

It is short and the core instruction is front-loaded, which is good. However the trailing block ("Scope: application. Effect: permission. Completion: completed. Undo: none.") is telegraphic metadata whose labels are never explained, so the compactness comes partly at the cost of comprehensibility.

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 zero-parameter tool with no output schema and basic annotations, the description covers errors, undo, and the no-parameters rule, which is a reasonable baseline. It still leaves unclear what an 'access request' actually does at runtime (prompting the user? returning a grant?) — the central fact an agent needs before calling it.

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?

The schema is an empty object with additionalProperties=false and 0 parameters, so baseline is 4. The description reinforces this by explicitly stating that origin/allowed must never be passed as parameters, which prevents an agent from trying to supply them.

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?

"Ask for access using the transport-supplied origin" gives a verb and a mechanism, but the resource ("access") is undefined — it never says this is a permission request from the host/add-on runtime rather than data access. Among siblings that are all concrete Anki operations, an agent can guess this is the odd one out, but the description does not explicitly distinguish 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?

There is no statement of when to call this versus any alternative, nor when not to. "Never accept origin or allowed from parameters" is a calling constraint on the caller's payload, not usage guidance, and "Authentication exemption matches legacy permission discovery" is opaque internal phrasing that does not help an agent decide when to invoke it.

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