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

Beyond the destructiveHint=true annotation, the description discloses that secrets are stored encrypted and never returned, that an existing same-level/scope/path/key variable has its passed fields replaced (explaining the destructive behavior), the required memory:moderate permission, and where the value physically lands (file path vs env var). This is unusually rich behavioral context.

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 dense but front-loaded, opening with the purpose before moving to secret handling, upsert semantics, level permissions, and path behavior. Every sentence carries information, though it packs several distinct concerns into a single long paragraph.

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 12-parameter mutation tool with no output schema, the description covers the highest-risk behaviors (overwrite, secret encryption, permissions, storage location) and notes that secrets are not returned. It omits any mention of return values or error cases, but with a 100%-covered schema and destructive annotations this is close to complete.

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 100%, so the baseline is 3, but the description adds real meaning: 'path' determines the file /run/agent/vars/<path>/<key> on the agent VM while omitting it produces an environment variable, and 'level' values are tied to permissions and ownership. It still leaves type/jobs/desc/title/allCompanies behavior entirely to the schema.

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 states a specific verb and resource ('Saves a variable') and adds the intended use case ('when the user asks to keep a value') plus the storage destinations (file under /run/agent/vars vs environment variable). It never names a sibling such as memory_create, so an agent cannot tell from this text alone how it differs from the memory_* family.

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 gives a clear trigger ('when the user asks to keep a value') and prerequisites (company/project/repository levels need memory:moderate). It does not name an alternative tool or say when NOT to use this one, so the routing guidance is context-rich but not exhaustive.

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