red_flag_screen

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

The description goes beyond the readOnlyHint and idempotentHint annotations by explicitly stating that the tool 'invents no new evidence' and 'renders no investment verdict.' This provides crucial behavioral context about its non-generative, non-decisive nature, which is not fully covered by the annotations alone.

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 a single paragraph that is informative but slightly verbose, repeating the idea of 'you've already gathered' and 'pass through' multiple times. It is well-structured and front-loads the main purpose, but could be tightened without losing meaning.

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 explains the output format (severity-bucketed flag list with overall severity) and the constraint that flags trace to supplied data. It also clarifies that omitted categories contribute no flags. It does not detail how severity is calculated, but that is likely an internal implementation detail. Given there is no output schema, this level of description is sufficient for an agent to know what to expect.

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 descriptions are provided for 4 of 6 parameters (litigationCases, negativeNewsCount, promoterRegulatoryHits, plausibilityIssuesByPeriod) and are helpful in linking them to source tool outputs. However, companyName and monthsSinceLastFunding lack any description, and the tool description does not clarify them. The 67% coverage is moderate, but the missing explanations for these two parameters leave ambiguity.

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 clearly states the tool's function: aggregating evidence from specified sibling tools (litigation_history, negative_news, ratio_analysis/financial_statements, promoter_background) into a severity-bucketed flag list with an overall severity. It distinguishes itself from those source tools and from report generators by focusing on screening and aggregation.

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 explains when to use the tool (after gathering evidence from the listed tools) and that all inputs are optional, allowing partial usage. It also clarifies that it renders no investment verdict, which helps avoid misuse. However, it does not explicitly contrast with sibling tools like generate_report, leaving some ambiguity about when to prefer this tool over a full report.

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