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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds two useful behavioral facts: omission uses documented defaults, and legacy tests are supported. It says nothing about pagination interactions with the default limit of 100 or how filters combine, so it adds only moderate value.

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 short sentences, front-loaded with what is returned before the targeting mechanics. No filler, though 'exact refs' is slightly opaque phrasing that could be spent on filter semantics instead.

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?

An output schema exists, so return values need not be explained, but an 8-parameter tool with 13% schema coverage needs the description to pick up the slack on level/status/category/reviewScope filters. It does not, so an agent cannot tell how to narrow a result set that defaults to 100 items.

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?

Only blockId has schema description coverage (13% of 8 params), so the description carries the burden of explaining the rest. It covers block/run targeting but is silent on level, status, category, reviewScope, limit and testId, leaving half the filter surface undocumented in both places.

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 and resource ('List accessibility criteria') plus the payload shape (status and exact refs), which is more than a restatement of the name. It does not explicitly differentiate itself from the singular get_success_criterion or list_accessibility_tests, but the plural list plus the returned fields make the intent readable.

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?

It routes the agent to list_test_blocks as the source of block/run IDs and says omission falls back to documented defaults, which is real usage guidance. It never states when to prefer this over get_success_criterion or list_accessibility_tests, so the sibling selection decision is left implicit.

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