Advanced: raw session exec

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

Annotations only indicate readOnlyHint=false and openWorldHint=false, so the description carries the burden of disclosing side effects, security behavior, and operational details. It mentions 'FragGate-admitted on the MCP path' and 'Binding-only ops stay per-op proxy_fallback,' but these phrases are too jargon-heavy to be transparent to an agent. No clear explanation of mutation risks, permissions, or failure behavior is provided.

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 with the main purpose, which is good. However, several clauses are cryptic and likely do not help an agent ('FragGate-admitted on the MCP path,' 'Binding-only ops stay per-op proxy_fallback'). These sentences take up space without adding clear instructional value.

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 tool with four parameters, no output schema, no parameter descriptions, and advanced/internal positioning, this description is far from complete. It lacks guidance on parameter semantics, expected behavior, return values, error cases, and when to override the 'Prefer fraggate_call' advice. An agent would not have enough information to invoke this tool reliably.

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 0%, and the description does not explain session_id, slug, op, or payload. The only hint is that the session must already be open, which weakly relates to session_id. There is no meaningful guidance on how to construct op, slug, or payload, making correct invocation very difficult.

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 the tool's core function: 'Raw session exec for an already-open session.' It also names fraggate_call as the preferred alternative, which helps differentiate it from a key sibling. However, terms like 'FragGate-admitted' and 'proxy_fallback' are not defined, leaving some ambiguity about what 'exec' actually entails.

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 gives a clear usage signal by saying 'Prefer fraggate_call' and notes that this tool targets an already-open session, which implies a prerequisite. It does not, however, provide explicit conditions or scenarios where raw exec should be chosen over the preferred alternative, beyond labeling it 'advanced/internal.'

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