List knowledge suggestions

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 earns credit by adding operational context the annotations lack: required scopes (knowledge:read, luca:read), data sensitivity=redacted, and the underlying GET endpoint. 'Does not require idempotency' is redundant with idempotentHint rather than contradictory, but the auth/scope disclosure is genuinely useful.

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?

Purpose is front-loaded and the metadata lines (endpoint, scopes, sensitivity, idempotency) are compact and scannable. The payload description and the redundant 'Does not require idempotency' line each cost a little space, but nothing is verbose or disorganized.

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-value explanation is not required, and the description still helpfully sketches what a suggestion contains. For a read-only, non-destructive list with annotations covering safety, the only substantive omission is the semantics of the status filter, which is missing from both description and schema.

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 67%: the two workspace parameters are documented in the schema itself, and the description only reiterates the workspaceId/workspaceSlug override. Critically, the status filter (pending/approved/rejected) is undocumented in either the schema property or the description, leaving a real semantic gap. Baseline 3 fits when the schema does most of the work.

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+resource and characterizes the items unusually well: 'profile changes proposed from the coach's own knowledge sources, each with the excerpt it was drawn from and the value it would replace.' This clearly distinguishes a 'suggestion' from memories, insights, or learning proposals. It does not, however, name or contrast any specific sibling tool, so a 4 rather than a 5.

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?

The only usage-like sentence is about parameter overrides ('Use workspaceId or workspaceSlug to override the default workspace'), not about when to select this tool. There is no statement of when to call it versus the sibling list tools (knowledge_sources_list, learning_proposals_list) or how it relates to the approve/reject suggestions pair. Implied usage only.

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