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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral detail: shelf settings come back as status words and fields, and an entry returns notes, fields, picture, and logged sessions. It does not mention pagination limits for large shelves or behavior when a shelf name doesn't resolve, which are the remaining gaps.

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 compact clauses, each mapped to a call mode, with no filler sentences. The one inefficiency is the parenthetical list of shelf kinds, which spends lead-position space on examples rather than the core mode contract.

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?

With no output schema, the description carries the burden of describing returns, and it does so per mode (counts per shelf, settings plus entries, full entry with notes and sessions). For a five-parameter, all-optional reader it is nearly complete; missing are error cases for unresolvable shelf names and any indication of how large a shelf's entry list can be.

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 each parameter is already documented individually, and this sets the baseline at 3. The description adds only partial value beyond that: it clarifies the interaction between shelf and entry_id/title (narrowing from shelf to one entry) but says nothing about the sort parameter, which the schema covers on its own.

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 description names the resource precisely (custom shelves that hold kinds the main library doesn't cover, with concrete examples like board games, perfumes, concerts, wine) and enumerates three distinct modes of operation. It is distinguishable from neighbors like get_list or search_library, though the opening phrase 'Their shelves of their own' is elliptical and slightly obscures the verb.

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?

The three 'Without arguments / With shelf / With entry_id' clauses effectively give argument-driven usage guidance, so an agent can infer which call shape to use. However, nothing states when to prefer this tool over siblings such as get_list, show_item, get_details, or search_library when hunting for a single entry, and no prerequisites or exclusions are mentioned.

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