manage_rules

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

Goes well beyond annotations (which only say readOnlyHint=false, destructiveHint=false): it discloses the human-approval gate ("waits in the review queue until the user approves it themselves... no app can"), quota limits (25 rules / 2,000 chars), and that removal is a soft delete ("the rule is kept as removed"). No contradiction with destructiveHint=false, since removal is non-final and approval-gated.

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-loads the resource definition before the action breakdown and wastes no sentences. It is very densely semicolon-packed, which slightly hurts scannability, but every clause carries distinct information (limits, approval flow, exclusions).

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 7-parameter mutation tool with no output schema, the description covers action semantics, the approval workflow, quotas, soft-delete behavior, the project requirement, and even the return shape ("Returns the rule or {rules}"). Nothing an agent needs to invoke it correctly is missing.

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 adds real value by specifying the 300-char cap on `rule` and the requirement that `user_request` quote the user verbatim. `rule_id`, `model`, and `include_removed` are left entirely to the schema, so it doesn't fully compensate beyond baseline.

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 resource (a project's hard rules: short never/always rules shown first in every brief) and enumerates the three operations with their scope. It also explicitly distinguishes itself from the sibling log_work ("Preferences and lessons go in log_work"), so an agent can route 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 explicit trigger conditions per action: add "when the user states one", remove "ONLY when the user asks in this chat", plus a named alternative destination for other content. The exclusion on remove is stated emphatically and the alternative (log_work) is named.

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