Caly

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

Annotations already disclose destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the agent knows this is an unsafe, side-effecting, open-world execution. The description adds the isolated-sandbox context and the requirement that the program `return` its result, but it doesn't explain what 'short' means, concurrency limits, or what gets destroyed. It adds some value beyond annotations without contradicting them.

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 tight sentences, front-loaded with the core action and then pointing to server instructions. It's efficient, though the pointer to server instructions is a bit of a punt rather than self-contained 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?

For a single-parameter tool with full schema coverage and no output schema, the description covers the essentials: what it does and that the program must return its result. However, it defers the 'full contract' to server instructions and never mentions key behavioral facts (what tools are exposed as functions, whether external_* is always the prefix, error semantics), leaving meaningful gaps for an agent invoking it blind.

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 single `code` parameter is fully documented in the schema (including the `return` requirement and external_* function contract). The description adds no parameter-level detail beyond what the schema provides, so baseline 3 is appropriate.

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: runs TypeScript code in an isolated sandbox that calls Caly tools found via search_tools. This distinguishes it from the sibling search_tools, which only finds tools. It doesn't fully explain the program model (e.g., what 'short' means or what functions are exposed), but the core purpose is clear.

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?

The description implies you call it after finding tools with search_tools and that it's for short programs, but there's no explicit when-to-use vs. alternatives, no limits, and no exclusions. The deferral to 'server instructions for the full contract' leaves the agent without local guidance.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful context beyond them: the result is code-shaped (TypeScript declarations) and scoped to 'this connection,' which tells the agent the search is permission-bounded. It loses a point for deferring the actual contract to unstated 'server instructions.'

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 compact sentences, with the core purpose front-loaded and the sibling relationship in the first sentence. The trailing pointer to server instructions is functional but slightly hand-wavy rather than informative.

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 single optional-parameter, read-only discovery tool this is nearly sufficient: it conveys scope and output shape, and no output schema is needed. The remaining gap is that result size/limits and the referenced 'full contract' are left external, which could matter if the agent never sees server instructions.

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% and the single 'query' parameter is fully documented in the schema (case-insensitive substring over name/title/description, omit to return all). The description adds no parameter meaning on top of that, so the baseline of 3 applies.

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 ('Find') and resource ('the Caly tools this connection can call'), and specifies the return format (TypeScript declarations). It also names the sibling tool execute_typescript as the consumer of the results, so an agent can distinguish discovery from execution without opening either 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?

The phrase 'returned as TypeScript declarations to use from execute_typescript' implies the workflow (discover here, run there) but never states when to call this versus execute_typescript directly, nor any prerequisite. Usage is inferable rather than explicit, and there are no exclusions.

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