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

Annotations already establish readOnlyHint, idempotentHint, and non-destructive traits, so the bar is lower. The description adds essential behavioral context beyond annotations by explaining the mode-switching behavior (presence of crashId alters return payload). It does not contradict annotations, and for a simple read-only fetch, no rate-limit or auth disclosure appears critical here.

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 the core purpose and followed by a tightly worded conditional. Every clause contributes: the first identifies the resource, the second defines both branches of behavior. No redundant terminology, no filler.

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 3-parameter read-only tool with no output schema and no nested objects, the description covers the essential behaviors and the interplay between list/detail modes. It could hint at what a 'recent' crash means or confirm that the list contains crashIds for follow-up calls, but given the tool's relative simplicity, the gaps are minor.

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?

With 0% schema description coverage, the description carries the burden and largely compensates by explaining crashId's semantic role as the mode selector. While limit and bundleId aren't explicitly described, their semantics are low-ambiguity (numeric cap and app identifier), and crashId was the parameter most in need of clarification. Marginal gap remains on limit's transformation behavior in list mode.

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 opens with a specific verb+resource pair ('Fetch TestFlight crash data') that clearly scopes the tool's function and differentiates it from siblings like expo_testflight_feedback and expo_build_list. It further clarifies dual-mode behavior (list vs. full log), leaving no ambiguity about what the tool does.

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 each mode ('Without crashId, lists recent crashes. With crashId, returns the full crash log with stack trace'), giving clear conditional context. However, it doesn't explicitly name alternatives or exclusions (e.g., directing users to expo_testflight_feedback for feedback data, which is a natural sibling to distinguish from).

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