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

Annotations only cover readOnlyHint=false and destructiveHint=false, so the description adds the crucial disclosure that existing user-written text is overwritten and that the write is a full replacement, not a patch. There is mild tension with destructiveHint=false, but replacement-with-read-first is a non-destructive update pattern, so it reads as complementary rather than contradictory. It does not mention anything about authorization or who may edit whose guide, but on_behalf_of is documented in the schema.

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?

Front-loaded summary with the destructive warning and the follow-up workflow in one tight paragraph; the tag structure makes it scannable. The trailing returns block is short but labels the result as "writing style settings," which mismatches the research-guide subject.

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?

Low-complexity two-parameter tool with no output schema, and the description covers purpose, precondition, workflow, and a return summary — enough to invoke correctly. The only gap is the inaccurate framing of the returned value as writing style rather than the personalization guide, which could confuse an agent verifying the result.

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 100%, so baseline is 3; the description goes beyond by stressing that the whole new guide must be supplied back after a read, reinforcing the replacement semantics of the required guide parameter. It does not elaborate on the 20,000-character cap or the empty-string clear behavior, but those are already in the 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?

"Replace the user's personalization guide" names a specific verb and resource, then defines the resource as "how Sliq researches a person before writing to them." That definition separates it cleanly from the look-alike sibling set_writing_style_guide and from get_personalization_guide.

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?

Explicit gating condition: "call it only when the user asks to change how people are researched." It also gives the exact procedure for editing (read with get_personalization_guide, pass back the whole new guide), which is the main failure mode an agent would hit.

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