max_api_search

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

With no annotations, the description carries the full burden and does well: it discloses a caching layer keyed per-port, the real cost (~39,700 lines / 1.4 MB, 3.1–5.3 s), and that refresh invalidates the cache. It omits output shape and what happens on zero matches, but the performance/caching profile is unusually well disclosed.

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 the core claim, then examples, then an Args block — a clean structure. The parenthetical timings and three separate example invocations are slightly more than strictly needed, but the cost figure is decision-relevant and the examples double as usage guidance.

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, and the description sketches returns only loosely ('every class exposing that property + type'), but it covers scope, caching, cost, and all parameters — enough for an agent to decide and invoke correctly.

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 0%, so the description must compensate and does: keyword is a case-insensitive substring matched against class and member names, limit caps returned matches, and refresh rebuilds the cache (with the triggering scenario named). All three parameters gain meaning not present in the schema.

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 and resource ('Search the ENTIRE API surface ... classes and members') plus the underlying mechanism (dump `showClass "*.*"` then grep). Concrete example queries make the scope unambiguous and distinguish it from eval/python/scene-inspection siblings.

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 frames when to use it: the only way to answer 'does this Max have VRayLight?' without hallucinating from model memory, plus the refresh-after-install-plugins case. It does not, however, route the agent away from near-neighbors like max_api or max_doc, so no explicit exclusion is given.

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