cache

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

With no annotations, the description carries the full burden. It does disclose the destructive nature of 'invalidate' and the important default that omitting a key deletes ALL entries, which is genuinely valuable. However, it omits whether the cache is rebuilt automatically, permission requirements, and any rate or concurrency caveats.

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?

Front-loaded purpose sentence followed by a tight action list; every line earns its place with 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 two-parameter, no-annotation, no-output-schema tool, the description covers the action space, the key semantics, and even the fields returned by stats (key, age_seconds, ttl_seconds, expired). Only minor gaps remain around permissions and post-invalidation behavior.

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 0%, yet the description documents both parameters: action accepts stats/invalidate, and key is the optional target for invalidation with an explicit default-to-all behavior. That compensates well for the undocumented schema, though the action values are not formally constrained as enums.

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 ('Manage') and resource ('the local SQLite cache for static AF data'), and enumerates the two supported actions with one-line semantics. It is clearly distinguishable from the domain-resource siblings (projects, vulnerabilities, testcases, etc.), though it doesn't explicitly say it is the only cache-management tool among them.

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 action list implies when each mode is used (stats to inspect, invalidate to purge), and the note that omitting key purges everything is useful context. But there is no explicit when-to-use vs alternatives guidance, no statement of prerequisites or when cache invalidation is warranted.

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