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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is carried by structured data. The description adds real value with the visibility-consent rule and the implication that shelves are user-owned, but it never warns that setting fields replaces the entire existing list or that values survive only if keys are preserved.

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?

A single front-loaded sentence whose long list maps one-to-one onto parameters, so no clause is filler. It is dense but readable, with the visibility caveat correctly appended as a trailing 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?

For a destructive, open-world mutation with 10 optional parameters and no output schema, the description should say what a call returns and what happens to omitted or replaced data. It covers intent and one consent rule but leaves the agent guessing about partial-update behavior and the destructive replacement of fields.

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?

With 10 parameters and only 50% schema description coverage, the description does useful glossing -- 'what "by" means' for by_label, 'status words' for words, 'sessions on or off' for tracks_sessions -- but it leaves shelf vs shelf_id, the noun concept, and the replace-not-merge semantics of fields unexplained, and does not note that every parameter is optional so this is a partial update.

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?

Uses a specific verb (Change) plus resource (one of their shelves) and enumerates every mutable attribute: rename, noun, emoji, by-meaning, status words, fields, sessions, visibility. The name alone is not enough to separate it from edit_shelf_entry, and the description never draws that line, but the enumerated attribute list makes the operation's scope unambiguous.

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?

Contains one genuine guardrail -- 'Change visibility only when they ask' -- which is an explicit when-not rule. However, it never names alternatives such as edit_shelf_entry (per-entry edits) or set_hidden, and gives no prerequisites for when a shelf edit is appropriate versus creating a new shelf.

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