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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with discovery behavior. It adds useful context (public MCP is keyless; User MCP owns participant actions) plus a warning that listings/budget caps are not proof of funding or revenue, but says nothing about the return payload or what 'manifest' contains.

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 opening 'START HERE' is well front-loaded, but the paragraph then dumps ecosystem architecture and secondary-capability caveats, diluting the actionable guidance. It also contains an apparent typo ('SaSame'), and several sentences (Information Asset Exchange, Factory, Observatory) are tangential to this specific tool.

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 parameters and no output schema, the description bears more burden than it meets: it never explains what start_here itself returns or how an agent should consume it. It provides rich domain orientation but leaves the tool's own contract underspecified.

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 tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to clarify beyond what the empty schema already conveys.

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 front-loads 'START HERE' and paints the ecosystem (GEC, Demands, bidding, verification), implying this is an orientation/discovery entry point, but it never states concretely what calling start_here returns or does. The actual function ('manifest + best next call') lives only in the annotation title, not the description text.

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?

It explicitly routes the agent: 'First call gec_open_demands() for public-safe recruitable work' and distinguishes keyless Public MCP discovery from authenticated User MCP participant actions. It gives clear usage context and a concrete next step, though it doesn't say when NOT to call this tool.

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