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

Annotations already mark destructiveHint=true, but the description adds valuable context: 'Saving checks exact quotes and expected_version; it does not verify meaning or truth' and 'source deletion invalidates the capsule.' These disclose validation limits and lifecycle dependencies beyond the annotation flags, enhancing transparency.

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 short sentences, front-loaded with the primary purpose. Every sentence adds distinct information (purpose, content separation, validation behavior, constraints). No redundancy or 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?

Given the complex nested schema (state with 10+ fields, evidence references) and no output schema, the description is too sparse. It does not explain how to construct a valid capsule, what save vs. resume entails, or what happens on success/failure. Critical operational details are missing, making it inadequate for correct invocation.

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 0%, so the description must compensate by explaining parameters. It only references 'expected_version' and 'quotes' indirectly, without clarifying the action enum, name pattern, or the structure of the state object. Most parameters (goal, findings, hypotheses, etc.) are undocumented in the description, leaving agents to infer from the schema alone.

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 clear, specific action: 'Save or resume a structured task capsule.' It also clarifies the internal distinction between evidence-backed findings and hypotheses/open questions, which defines the tool's core purpose. This is not a tautology and distinguishes it from generic state tools.

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 usage for saving/resuming task capsules but does not explicitly state when to use this tool versus siblings like mithrandir_state or mithrandir_context_pack. It mentions constraints (same-account keys, source deletion) but no exclusions or alternative routing. Guidance is only implied.

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