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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds real substance: the result is the user's own settled reasoning held under their authority, it never instructs or decides, asks for no persona, and the served window echoes the query for auditability. That is useful disclosure beyond the structured hints, though it is entangled with philosophical asides rather than crisp behavior.

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?

It is a single dense run-on paragraph that does not front-load the action verb and dilutes the actionable signal with discursive passages such as 'it asks you to suppress nothing of your own read; what to make of it stays yours.' Useful sentences are buried, and several clauses restate each other (the verbatim rule appears twice).

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 read-only, idempotent tool with no output schema and fully documented parameters, the description covers the important unknowns: what comes back (the governing rulings in the user's own words), the query echo for drift auditing, and the session-token round-trip. It says little about the optional `scope` behavior, leaving one minor gap.

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 the baseline is 3, but the description adds genuine rationale the schema cannot: why `query` must be verbatim (lexical recall and the k-floor are calibrated on real turn text, paraphrases shift the gated lexeme set) and how `session` starts and continues a thread. That is meaningful semantic value above the schema's own parameter descriptions.

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 opening clause identifies the resource precisely — what the user has already decided about their own work (project, business, product, plan) and why — and the tool is distinguishable from siblings like get_from_unl or connect_to_unl. It is clear but phrased obliquely rather than as a crisp verb+resource, and the reader has to assemble the action from later sentences.

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 concrete trigger conditions: use it when the user's own work is in play (writing, planning, choosing) and when they ask what was decided, why something is so, or whether a choice was settled — explicitly noting the user need not say 'unl'. It never states when NOT to call it or names a sibling as the alternative, so it falls short of a 5.

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