set_prereq

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

Annotations provide idempotentHint=true and destructiveHint=false, so the safety profile is already declared. The description adds genuinely useful behavior beyond that: values are persisted ('Persisted values override MCP host ZEUS_* env defaults'), the tool explicitly excludes secrets, and presence flags only apply to credentials/LLM key. No contradiction with annotations.

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?

Purpose is front-loaded in the first sentence, followed by dense, purposeful guidance on secrets, URL handling, and persistence. Every sentence earns its place and there is no fluff, though six sentences make it slightly long; it could be tightened without losing information.

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 an 11-parameter tool with zero schema description coverage, the description covers the core flow well: secrets handling, URL-passing rules, persistence override, and presence-flag semantics. Output schema exists so return values need no explanation. But mode, role, auth_mode, and collection remain undefined, leaving meaningful gaps for such a complex, poorly-schematized 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 coverage is 0%, so the description must compensate, and it does for the most important parameters: zeus_url, bucket, scope (URL/sample passing rules) and the has_* presence flags ('Presence flags only for credentials and LLM key'). However, mode, role, auth_mode, and collection are never mentioned across 11 total parameters, leaving roughly a third of the surface unexplained.

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+resource: 'Store non-secret prereqs for readiness' and immediately negates what it does not do ('does not store password/token values'). This distinguishes it from the secret-handling context and from siblings like readiness_check and doctor, giving an agent a precise mental model of the tool's scope.

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?

Provides exceptionally explicit when/when-not conditions: pass zeus_url/bucket/scope when the user named a URL or sample in chat, leave zeus_url empty and wait for the form otherwise, and 'Do not copy the host ZEUS_URL.' The secret-vs-env-var routing ('Put real secrets in environment variables') tells the agent what must not go through this tool. No sibling is named, but the conditional guidance is detailed enough to drive correct invocation.

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