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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds real value beyond them: result cap and ordering ('Up to 12 works, closest first'), the exclusion rule for collection seeding ('not in it yet'), and the fact that collection mode requires a signed-in member's collection.

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?

Two dense sentences, front-loaded with the core semantics before the input modes and the result cap. Nearly every clause earns its place; only the em-dash UI analogy is slightly decorative.

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?

No output schema exists, so the description usefully discloses result count and ordering ('closest first'), which is the main thing an agent needs to interpret the return. The remaining gap is the unresolved relationship between 'Up to 12 works' and the limit parameter, plus no indication of what a returned work object contains.

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 67%, so the baseline is 3. The description reinforces the works count (1-5) and adds the 'signed-in member's collection' constraint and the 'not in it yet' filter semantics for the collection param. However, it never explains the limit parameter, and 'Up to 12 works' sits awkwardly against the schema's limit maximum of 100, leaving the agent unsure what limit controls.

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 verb+resource pair ('Works on Memorables that look like, or share the theme of, the works given') and anchors it to a familiar UI behavior ('More like this'). That recommendation semantics is distinguishable from search_works or get_work, though no sibling is named explicitly.

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?

Clearly explains the two invocation modes: seed with 1-5 works, or seed with one of the member's collections to get works 'in its spirit that are not in it yet'. Missing an explicit exclusion or a named alternative (e.g., use search_works when you want a query rather than a seed), which keeps it below a 5.

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