Shorty

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

Annotations already declare destructiveHint=true, openWorldHint=true, readOnlyHint=false, and idempotentHint=false, covering the safety profile. The description adds useful behavioral context (short program, isolated sandbox, orchestrates MCP tools) but does not elaborate on what can be destroyed, required permissions, or side effects beyond pointing to 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?

The description is two sentences and front-loads the core action. It is appropriately sized, though the second sentence defers the full contract to server instructions rather than being self-contained.

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?

Given the rich annotations, an output schema, and 100% schema description coverage, the description is nearly sufficient. It explicitly points to server instructions for the full contract, which covers the remaining complexity for this open-world destructive execution tool.

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 schema already documents the single code parameter thoroughly. The description adds only minor framing (short program, orchestrating tools found via search_tools) and does not add syntax or format details beyond 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?

The description states a specific verb and resource: run a TypeScript program. It also clarifies the program's role (orchestrating Shorty MCP tools found via search_tools) and the environment (isolated sandbox), distinguishing it clearly from the sibling search_tools.

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 gives clear context by stating that the TypeScript program orchestrates tools found via search_tools, implying the prerequisite of discovering tools first. However, it does not state explicit exclusions or when not to use this tool versus alternatives.

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 declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds useful context beyond that: results are scoped to tools 'this connection can reach' and are returned as TypeScript declarations. Deferring the full contract to server instructions is honest but slightly defers rather than discloses.

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 sentences, front-loaded with purpose before output format and the pointer to server instructions. No redundant restatement of the title or 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?

An output schema exists, so return values needn't be explained, and the annotations carry the safety profile. The description covers what the tool does and how its output is consumed; only the server-instructions pointer leaves an agent dependent on external text for the full contract.

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 there (case-insensitive substring against name/title/description; omit to return all). The description adds nothing about parameter syntax or matching semantics, so baseline 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 and resource ('Find the Shorty MCP tools this connection can reach') and goes further by naming the output form (TypeScript declarations) and the sibling it feeds into (execute_typescript). An agent can distinguish it from execute_typescript 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 workflow context is clear: this is the discovery step whose output is passed to execute_typescript. However, it gives no explicit when-not guidance (e.g. when to search vs. call a tool directly), and the 'omit query to list all' behavior lives only in the schema, so it stops short of a 5.

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