get_failure_screenshots

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

No annotations provided, so the description carries the full burden. It discloses that it returns presigned S3 URLs and that they can be viewed with the Read tool, which is useful operational context. However, it doesn't mention URL expiration, permissions needed, or behavior when no failures exist.

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 sentences, front-loaded with purpose, followed by a useful operational note about viewing URLs with the Read tool. No waste.

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 a 5-param read tool with no annotations and no output schema, the description covers the purpose and return type well but omits when to choose it over siblings, any limitations, or error behavior. Adequate but leaves gaps.

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 description coverage is 100%, so all parameters are documented in the schema with defaults and meanings. The description doesn't add parameter-level detail beyond saying 'recent test failures', which aligns with the days parameter. Baseline 3 applies when schema fully covers params.

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 (get) and resource (failure screenshots from recent test failures). It's clear what it returns, but it doesn't distinguish itself from the many sibling tools like get_recent_failures or get_failure_patterns beyond the 'screenshots' aspect.

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 implies usage — viewing what the UI looked like when a test failed — but doesn't say when to use this vs. siblings like get_recent_failures. No explicit when/when-not guidance.

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