access_change

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

No annotations are supplied, so the description carries the full behavioral burden, and it does unusually well here: it discloses deferred-approval semantics, that the user is notified, and that the agent cannot self-approve. It still does not say whether 'hide' merely conceals or actually destroys memory content, nor whether a widening request can be revoked, which matters for a mutation tool with zero annotation coverage.

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?

Every sentence carries content, but the formatting is poor: nested colons and inline quoted enumerations ('change: "hide" (narrow: applies at once) or "show" / "level" / "only"') make it read as a run-on fragment chain rather than front-loaded guidance. The asymmetry between narrow and widen is the most important fact and is buried mid-sentence.

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 three-required-parameter mutation tool with no annotations and no schema descriptions, the description covers the critical gaps: value vocabulary, approval flow, notification, and permission limits, and an output schema exists so return values need no explanation. Reversibility and the destructive/no destructive nature of 'hide' remain unaddressed.

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 0% and no parameter has an enum, so the description is the only source of value vocabulary — and it supplies it for all three parameters (change modes with semantics, a client list plus 'every AI', and section/level examples for 'what'). The 'what' list is explicitly open-ended ('sections such as'), which leaves the agent guessing about unrecognized values.

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: 'Change what an AI agent may see in the user's long-term memory', and distinguishes the narrowing case from the widening case. It never names the sibling access_status, so an agent must infer for itself which tool to consult for current permissions, but the action itself is unambiguous.

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?

Gives explicit conditional guidance: 'hide' applies at once, while 'show'/'level'/'only' never applies from here and instead becomes a request the user approves by typing. It also states 'You cannot approve a request, yours or another's', which directly tells the agent the limits of what this call can accomplish. What is missing is routing guidance toward access_status for checking existing permissions.

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