EGA V9 MCP

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

Annotations are absent, so the description carries the full behavioral burden. It discloses that a 'governance decision and evidence' is returned, but says nothing about side effects, whether the workflow is actually executed or only evaluated, permissions needed, synchronous behavior, error semantics, or whether the 'governance decision' is deterministic.

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 short and front-loaded: it states a purpose and immediately follows with the return value. There is no filler or structural waste. However, brevity is partly achieved by omitting essential domain detail, so it does not earn a perfect score.

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 governance/execution tool with no annotations, no output schema, and no sibling context, the description leaves critical information missing: what EGA V9 is, what 'govern an AI workflow' operationally entails, how expected_replay_root is used, what the decision/evidence look like, and what failure conditions exist. An agent cannot safely invoke this tool based on this text alone.

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 baseline is 3. The tool description itself adds no parameter semantics, and the schema descriptions are partially weak: workflow_json is explained, but expected_replay_root is described as 'Optional' despite being in the required array, which is confusing. The description does not compensate for this ambiguity.

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 restates the tool's name ('Govern an AI workflow' mirrors ega_govern_execution) and adds only the vague qualifier 'canonical EGA V9 execution path'. It does not specify the concrete operation's effect, what 'govern' means in practice, or how this tool differs from any alternative (no siblings are provided).

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?

There is no when-to-use guidance, no prerequisites, no exclusions, and no alternative tools mentioned. The phrase 'canonical execution path' hints that this is the intended route, but the description never states conditions under which an agent should select this tool or what state the workflow must be in.

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