compute_endpoint_list

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

Thoroughly describes that only accessible endpoints are returned and includes role filtering. While read-only nature is implied, no annotations exist, and the description does not explicitly state it is side-effect-free, but the level of detail is high.

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 concise yet comprehensive, with clear sections (purpose, note, args, returns, examples). Each sentence adds value, and the structure allows quick scanning.

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 presence of an output schema, the description adequately summarizes the return format. It covers the core functionality, parameter, and provides examples, leaving no critical gaps for an AI agent.

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?

The description provides complete semantic detail for the 'role' parameter beyond the bare schema: it defines the filter, lists acceptable values ('any', 'owner'), and specifies the default, fully compensating for 0% schema description coverage.

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 clearly states 'List Globus Compute endpoints accessible to the current user' and explains its use for finding a UUID by name, distinguishing it from siblings like compute_endpoint_status and endpoint_search.

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 advises when to use (to match user's request against display names) and when not to (keyword search not available as for Transfer endpoints), with a clear fallback instruction to ask for UUID.

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