memshelf_shelve

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

Description discloses key behaviors beyond annotations: redacts credentials, enforces digest contract, returns errors with exact fixes on violation, never pushes, and returns address/redaction report/warnings. No contradictions 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?

The description is four sentences with a clear lead sentence and bullet-like details. Each sentence adds value, no redundancy, and front-loads the primary purpose.

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's complexity (many parameters, output schema exists), the description mentions return values but does not detail all inputs or the output structure. It provides moderate completeness but leaves gaps for parameter semantics and full behavioral edge cases.

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 must compensate, but it only explains the digest parameter indirectly (<=120 words, named referents, no secrets). Other important parameters like shelf_path, slug, kind, and tags are not described. The description adds behavioral context but not per-parameter clarification.

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 offloads a closed topic to a shelf as an episode, with specific verbs like 'redacts', 'enforces', 'composes', 'writes', 'appends', and 'auto-commits'. This distinguishes it from sibling tools like recall, search, or index.

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 implies use for closed topics via 'offload one closed topic', and notes auto-commit behavior and error handling for contract violations. However, it lacks explicit guidance on when not to use or direct comparisons to alternatives like memshelf_import.

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