ecosystem_scan

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

With no annotations provided, the description carries the full disclosure burden. It transparently discloses that this writes to the DB (update ecosystem_repo_profiles), sets needs_deep_review=True conditionally, auto-classifies heuristically, and supports a dry_run mode to avoid writes. This is honest about the mutating nature and workflow impact, though it doesn't detail destructuring of existing profiles or idempotency behavior, keeping it shy of 5.

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 structured with a clear summary sentence, a bulleted query list, and a closing behavior note. It's efficient and scannable. Slight redundancy exists between the prose explanation and the parameter schema docs for min_stars, and the query list could arguably live in the output schema or be trimmed, but overall it's well-organized without 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?

The tool is moderately complex (8-10 queries, dedup, classification, conditional flags) and has a rich output schema. The description covers the query set, filtering logic, and side-effect behaviors well. A short note on expected duration or idempotency when re-running would strengthen it, but the combination of description plus schema is nearly complete for agent use.

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 the schema already documents both parameters thoroughly. The description reinforces min_stars as a popularity floor and maps values to strategy (full vs incremental), which adds some nuance. However, this largely echoes schema content; baseline 3 is correct since the description adds modest value over the schema's detailed parameter docs.

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 states a specific verb+resource action: 'Scan popular Claude ecosystem repos (>=min_stars) and update ecosystem_repo_profiles.' It clearly enumerates the 8-10 gh search queries and the filtering/dedup logic. While sibling ecosystem tools exist, this one is clearly the scanning entry point, differentiated by its concrete query list and update behavior.

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 details mechanics (queries run, thresholds, classification heuristics) without explicit when-not-to-use guidance. However, sibling names like ecosystem_scan_periodic suggest a periodic variant, and the description's threshold rules imply when to invoke (full vs incremental sweeps). It lacks explicit exclusions naming alternatives, so 4 is appropriate.

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