Execute GitHub Action

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

Goes well beyond the annotations by disclosing that output is lossily compressed via strict token projection filters (URLs, avatar links, empty hashes, node_ids stripped) with a claimed 70%+ token saving, and that mutation is environment-gated. That output-truncation disclosure is exactly the kind of behavior an agent cannot infer from readOnlyHint/destructiveHint alone.

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?

Three dense sentences that are front-loaded with the execution contract before moving to prerequisites and output behavior; little waste. The '70%+ token savings' claim borders on promotional but still conveys expected output shrinkage.

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 no output schema, the description carries the return-value burden and does so adequately via the format enum and compression note, and it covers the dynamic-parameter discovery path. It leaves error behavior for blocked mutating actions and partial-schema mismatches unstated, which is a minor gap.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning for the polymorphic 'params' object by framing it as the argument dictionary matching the selected action's own schema and pointing to github_find_actions as the way to learn that schema. The static schema cannot express that per-action contract, so the description earns above baseline.

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 (execute) and resource (a named action from the 75-action catalog) with the dispatch mechanism spelled out: action name plus argument dictionary. It is clearly separable from github_find_actions, which is named as the discovery step rather than the executor.

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?

Gives an explicit prerequisite (the exact action name must come from github_find_actions) and an explicit environmental exclusion (mutating actions blocked under GITHUB_READ_ONLY=true). It does not clarify when to prefer this generic dispatcher over typed siblings like get_file_contents or get_repository, which overlap with catalog actions.

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