OSA Procurement Guard

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

Annotations provide little (readOnlyHint=false, openWorldHint=false) and nothing contradicts them. The description adds context about the decision inputs and the need to obtain an OSA API key, but it does not disclose whether the call has side effects, makes an external network request, or how the key is supplied.

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?

Two dense sentences front-load the action and outcome and then give the key setup URL. Every phrase adds information; there is no filler or repetition of the schema.

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 only enumerates ALLOW/HOLD/DENY without specifying their format or what triggers each verdict. Given eight parameters and almost no parameter guidance, an agent would still be guessing about valid invocations and required setup.

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?

Only 38% of schema properties have descriptions, and the tool description barely compensates: 'budget policy' and 'cheaper equivalents' only loosely map to price/capability fields. It does not explain asset, network, min_trust, max_price_usd, offered_price_usd, or the anyOf requirement between name and endpoint.

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 purpose: call before buying an API/MCP tool and return ALLOW/HOLD/DENY. The decision inputs (budget policy, trust evidence, price history, cheaper equivalents) further clarify what the tool evaluates. No siblings exist, so no differentiation is needed.

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?

Explicitly tells the agent when to invoke it ('before buying an API or MCP tool') and supplies an API-key acquisition URL, signaling an auth prerequisite. There are no alternative tools or exclusions, so no when-not-to-use guidance is possible.

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