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

Annotations already declare readOnly/idempotent/openWorld=false, so safety is covered. The description adds real behavioral context beyond that: dataset size (~8,900), fuzzy matching over title/author/description, and parity with max4.live, plus default-sort fallback behavior. It does not discuss pagination or result-shape limits beyond the schema's limit field.

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-loaded with purpose, then matching semantics, then a single high-value composition example. The example sentence is long but earns its place by showing cross-parameter reasoning; only minor trimming is possible.

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 agent would benefit from knowing the return shape (fields per device, whether pagination exists), which is not stated. Everything else needed to call it correctly — filters, defaults, sorting, empty-query behavior — is present, and annotations carry the safety profile.

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 baseline is 3, but the description adds compositional meaning the schema does not: a worked example translating 'popular free MIDI devices from the last 2 weeks' into type=[MIDI Effect,MIDI Generator,MIDI Transformation], license=[free], sort=downloads, added_after=<date>. That teaches multi-parameter interaction, not just individual fields.

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?

Specific verb+resource+scale: 'Search ~8,900 Max for Live devices for Ableton Live', with the matching strategy (fuzzy full-text over title/author/description) stated up front. An agent can distinguish it from get_device (single-device lookup) and list_filters (facet enumeration) without opening a schema.

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?

Explicitly tells the agent when to omit query ('Omit to browse by filters only') and gives a concrete natural-language composition example mapping intent to type/license/sort/added_after. It does not explicitly name when to prefer get_device or list_filters, so it stops short of full when/when-not routing.

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