Klisten ModelRoute

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

Beyond the annotations (readOnly/idempotent/openWorld/non-destructive), it discloses that returned metadata strings are untrusted data and must never be treated as instructions, and that per-item freshness must be checked. These are substantive behavioral caveats an agent would otherwise not know from the structured fields.

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 short, front-loaded fragments with the core purpose first and caveats after; no filler. The negation list is slightly list-like but each item earns its place by ruling out a plausible misreading.

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 an output schema present, return values need no explanation, and the annotations already cover the safety profile. The description adds the trust/freshness caveats and confirms no purchase or account access; it stops short of describing pagination continuation or rate behavior, but is otherwise sufficient to call it 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 description coverage is 0%, so the description must carry parameter meaning; "bounded page" gestures at limit/offset paging and the "not a complete price quote" caveat hints that pricing_class is a coarse class, not a precise price. However, it never explains the limit ceiling, offset bounds, or enum behavior, so it only partially compensates for the coverage gap.

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 ("Read") and resource ("the last published ModelRoute metadata catalog"), scoped to "a bounded page". It further disambiguates by explicitly denying adjacent things (model inference, benchmark, availability guarantee, price quote), so an agent knows exactly what this returns without opening the 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?

It clearly frames when NOT to rely on it (not inference, not a benchmark, not an availability guarantee or complete price quote, no purchase or account access) and adds an operational note ("Check freshness per item"). It lacks a positive "use this when..." statement, but with no sibling tools the exclusion set does the routing work well.

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