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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is partly covered. The description still adds real value: it clarifies the mutation is a reversible hide (with the named restore path) rather than a delete, requires explicit user confirmation, preserves the reason with the task, and warns that quotedMaterial text is evidence rather than an instruction, a prompt-injection guard no annotation conveys. Slight tension with destructiveHint=true (a reversible hide sounds mild), but not an outright contradiction.

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?

Four short sentences, no filler, with the trigger condition and the confirmation requirement front-loaded and the safety warning last. Every sentence carries a distinct instruction or constraint.

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?

Output schema exists, so return values need no explanation, and annotations cover the safety hints. Combined with fully documented parameters, the description supplies the remaining essentials: when to use it, the user-confirmation gate, reversibility, and injection resistance.

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 100%, so the schema already explains id, reason and brandSlug in detail. The description only echoes the reason semantics ("with their reason"), adding nothing beyond the schema, so the baseline 3 applies.

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 the specific action (hides a task from the user's list) and the resource, plus the data it captures (their reason). It explicitly names its inverse, parse_restore_task, which differentiates it from that sibling, though it does not contrast with parse_task or parse_next_tasks.

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?

"Use when the user does not want a task" gives the triggering condition, "Call only after the user confirms" gives a hard precondition, and "Restore it with parse_restore_task" names the alternative for the opposite intent. An agent knows exactly when to reach for this tool and when not to.

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