screen_candidate

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds critical behavioral detail: it is 'offline, read-only, propose-only', fetches price history on demand if not cached (unless ASSET_MCP_OFFLINE is set), and explicitly states it is not a buy recommendation or return forecast. This goes beyond what annotations provide.

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 three sentences with no redundancy. It is front-loaded with the main action and criteria, then adds behavioral details and a critical negation. Every sentence adds value without wasting words.

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?

The description fully addresses the tool's purpose, behavior, constraints (offline, read-only, cache behavior), and what it is not. With one parameter and an output schema present, nothing more is needed for the agent to understand and correctly invoke the 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?

Only one parameter 'ticker' with schema coverage 0%, but the description references 'TICKER' multiple times, explaining it is used to fetch price history and evaluate against the user's book. This adds meaning beyond the schema's minimal definition, though it could be more explicit about the expected format (e.g., ticker symbol string).

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 uses the strong verb 'Judge' and specifies the resource 'NEW ticker against the user's book'. It lists the evaluation criteria (cost, liquidity, age, etc.) and explicitly contrasts with sibling tools by noting it is offline, read-only, and propose-only. It also states the intended use case: 'Use to answer "is TICKER a good fit"'.

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 clearly directs when to use the tool: 'Use to answer "is TICKER a good fit"'. It also explicitly states what the tool is not ('Never a buy recommendation or a return forecast'). However, it does not provide explicit guidance on when to avoid using it or differentiate it from siblings like propose_allocation or portfolio_summary beyond the inherent purpose.

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