project_index_refresh

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

Annotations only indicate mutation and not read-only. The description adds behavioral context beyond annotations: handling of unknown freshness in if_stale mode, counting unindexed files as stale, and returning freshness summaries. No contradiction with annotations.

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?

Three sentences with no wasted words. The first sentence efficiently packs the main purpose, conditions, and output. The second adds mode specifics. Slightly dense but still clear. Could benefit from more structured presentation.

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 has 4 optional parameters and an output schema (not shown), the description covers main behavior and modes. However, parameter semantics are missing, limiting completeness. Output schema existence mitigates need to detail return fields, but parameter descriptions are needed.

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 0%, and the description does not explain the individual parameters (projectId, projectRef, mode, reason). Only 'mode' is implicitly referenced. With zero coverage, the description should compensate but fails to add meaning for 3 of 4 parameters.

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 it is a mutation tool for index freshness, specifies conditions (stale, unknown, deleted, unindexed), and lists output (before/after summaries, new index run). This distinguishes it from siblings like project_index_status.

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 (when snapshot is stale, unknown, deleted, or has unindexed files) and the behavior of 'if_stale' mode. However, it does not explicitly contrast with sibling project_index_status or provide when-not-to-use guidance.

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