find_suspicious_releases

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

Annotations declare read-only and closed-world, so safety is covered. The description adds domain logic beyond annotations: which indexer sent the release, criteria distinguishing 'fake' vs 'early_release' based on import status, and that it scans queue, history, and blocklist.

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?

Front-loaded purpose followed by compact detection criteria and representative examples; no filler. The semicolon list is dense but each clause adds detection detail.

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?

Output schema exists, so return details are unnecessary. For a read-only, two-optional-param diagnostic tool, the description covers what is detected, why, and example queries, leaving no critical 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 coverage is 100%, so both parameters (days, service) are already documented in the schema. The description adds no further semantics about them (e.g., default day range or dual-service behavior). Baseline 3 is correct.

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 ('Detect') and resource ('fake/malicious releases'), and enumerates the three detection patterns (executables in queue/history/blocklist, early grabs, same-size different-episode downloads). Distinguishes from sibling inspection tools like get_history or find_orphan_downloads by its fraud-signal focus.

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?

Supplies example questions it answers, clarifying intended use, but does not explicitly name when to use get_history or get_blocklist instead or when this tool is inappropriate. Context is clear without exclusions.

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