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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds context the annotations cannot: the account-wide visibility model, the decoupling of listing from per-agent attachment, and the requirement for the "Agents" permission on the plan. Only the return shape/pagination is undisclosed.

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: what the entries are, their scope, then the attach caveat and permission note. Every sentence carries distinct information and the identity of the resource is front-loaded.

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 read tool with no output schema, the description covers scope, permission prerequisites and the relationship to kb_attach. The one remaining gap is that it never hints at what a listed entry looks like (fields, IDs, pagination), which matters more here since there is no output schema to fall back on.

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 tool takes zero parameters, so the baseline is 4. The description correctly describes no filtering or paging inputs, consistent with the empty, additionalProperties=false schema.

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 defines the resource precisely by enumerating its kinds (crawled URLs, uploaded files, pasted text) and its scope (account-wide), which lets an agent distinguish it from kb_upsert, kb_delete and kb_attach. It does not itself state the verb 'list' – that only appears in the title and in the incidental phrase 'an entry listed here' – so it falls just short of the verb+resource ideal.

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?

It gives real decision context: entries are account-wide, and being listed here does not mean an entry is in use, because usage is set per agent via `kb_attach`. That is enough to steer an agent toward this tool for discovery and toward kb_attach for wiring. It stops short of an explicit 'use this before calling kb_attach' instruction or any exclusion.

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