capture_put

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

Annotations already declare readOnlyHint=false and non-idempotent, so the write nature is covered structurally. The description adds value by disclosing the return payload ('returns id + preview') and the backing store (FTS5), but says nothing about durability, dedup, or how the id is later used with capture_get.

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?

A single front-loaded sentence with no wasted words, delivering action, destination, and return value in one pass.

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?

No output schema exists, so the description appropriately spells out the return (id + preview), and params are fully documented in the schema. Minor gap: no routing guidance to the retrieval siblings that consume the returned id.

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 schema already documents all six parameters and the baseline is 3. The description adds no parameter-level detail (e.g., what 'preview' truncates or how tool_name keys retrieval) beyond what the schema provides.

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 (sandbox/capture) and resource (verbose tool output) and names the destination store (FTS5) plus the return shape (id + preview). An agent can tell what it does, but it does not explicitly distinguish itself from the capture_get/capture_search family by name.

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 phrase 'sandbox a verbose tool output' implies the scenario, but there is no explicit when-to-use, no prerequisites, and no named alternative among the many capture_* and memory_* siblings. An agent must infer that this is the write side of the capture family.

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