get_recent_changes

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

With no annotations, the description carries the full burden. It discloses the version requirement, read-only nature ('no content reads'), and the specific drift buckets. This is transparent, though it lacks details on pagination, limits, or error handling.

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 extremely concise, consisting of three short clauses that convey purpose, usage context, and a behavioral hint. Every word earns its place, and the key information is front-loaded.

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?

Given the tool's simplicity and lack of output schema, the description provides a solid understanding of input, purpose, and behavior. However, it does not specify the output format, which might leave an agent guessing about what 'list sections' returns.

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 describes parameters well. The description adds some context by referencing the FreshnessProbe and bucket names, but this does not significantly enhance understanding beyond what the schema provides.

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 that the tool lists sections whose source has drifted from index state, specifically identifying two buckets (edited_uncommitted and stale_index). It also positions the tool as a pre-flight check before re-indexing, distinguishing it from siblings that may perform actual re-indexing or deeper analysis.

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 explicitly says 'Pre-flight check before deciding whether to re-index', providing a clear use case. However, it does not mention when to use alternative tools like 'check_embedding_drift' or 'get_stale_pages', so the guidance is good but not exhaustive.

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