clo_api_call

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

No annotations are present, so the description carries the full behavioral burden — and it delivers: it discloses the JSON serialization format, that non-JSON returns get session handles, that 'a false result is NOT success,' and that timed-out mutations should not be blindly retried. These are exactly the non-obvious behaviors an agent needs for a generic dispatcher, none of which any schema could convey.

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?

The purpose is front-loaded and every sentence carries real value — the safety and retry warnings earn their place for a generic dispatcher. It is slightly dense (six distinct pieces of guidance in a single paragraph), but that density is justified given the complexity and the absence of annotations.

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?

For a generic dispatcher with no output schema and no annotations, the description covers purpose, arg construction, handle behavior, and safety. The main gap is error semantics — it warns that false ≠ success but never states what an error looks like (exception vs error object) — though the 'read live documentation first' directive mitigates this since each function's behavior is documented elsewhere.

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 compensate. It explains the JSON argument syntax ({$type...}, {$enum...}, {$handle...}), which is the hardest part of constructing args. However, it does not explicitly document the 'name' parameter (only implied via 'discovered in clo_api_catalog') or the 'kwargs' parameter, leaving those to inference.

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 action ('Call any public function discovered in clo_api_catalog, or read a constant') with a clear verb and resource. It distinguishes itself from the discovery/documentation siblings (clo_api_search, clo_api_doc, clo_api_describe) by being the execution tool — an agent can tell it apart without opening their schemas.

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?

Provides clear usage context: 'Read its live documentation first' implies checking docs before calling, and 'Use checkpoint_save before risky scene edits' gives a concrete when-to precedent. However, it never explicitly names the alternative tools (clo_api_doc, clo_api_search) or gives a when-not-to-use exclusion, so differentiation is implied rather than stated.

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