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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds value beyond them: edits are applied sequentially, an empty oldStr appends, and a non-matching passage fails with a `validation` error that returns current content. That failure-mode disclosure is exactly the kind of context annotations can't convey. It stops short of describing what happens to the rest of the document if an edit mid-list fails (partial application vs. atomic rollback), which is the one behavioral question an agent would still have for a multi-edit destructive tool.

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 sentences, front-loaded with the core operation, then the routing rule, then the failure mode. No filler and no repetition of the title.

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 destructive, non-idempotent mutation with no output schema, the description covers operation, ordering, append behavior, failure semantics, and sibling routing. The gaps are the unexplained `websiteId` and whether a mid-list failure leaves earlier edits applied.

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 50% and the nested `edits` object is already thoroughly documented in the schema (including exact-once matching, replaceAll, and append-on-empty), so the description mostly restates it. The undocumented `websiteId` parameter is never explained in either place — the description never clarifies whether it identifies the site whose project knowledge is targeted.

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 (applies exact-match text edits to the user's project knowledge text) plus ordering semantics. It also differentiates from the nearest sibling by naming where agent-discovered facts belong (agent notes), so an agent can separate it from websiteKnowledge_agentNotes_edit and websiteKnowledge_update without opening schemas.

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 an explicit when-to-use constraint ('Change it only when the user asks') and an explicit routing alternative ('agent-discovered facts belong in agent notes'). This is a genuine use/don't-use rule with the competing tool named, not implied guidance.

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