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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool saves data, implying a mutation, but does not disclose whether it overwrites existing data, whether it requires prior authorization or a completed deep scan, whether it is idempotent, or what happens on repeated calls. The parenthetical listing data categories adds some clarity but does not address side effects.

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 a single, compact sentence with no filler. It front-loads the core action ('Save the output of a deep scan') and appends the clarifying parenthetical. It earns a high score for economy, though it sacrifices some necessary detail in doing so.

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 tool with one required parameter, no output schema, and no annotations, the description must at least specify what the parameter means, any preconditions, and likely effects. It only partially hints at the parameter's meaning via 'onto the agent' and never explains preconditions or return behavior, leaving an agent under-equipped to invoke it correctly without additional investigation.

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?

The schema has one required string parameter 'id' with no description, and schema description coverage is 0%. The description mentions 'onto the agent,' giving a weak hint that 'id' likely identifies the agent, but it never explicitly states what the id refers to, what format is expected, or whether it could be a scan id. This is insufficient compensation for a completely undocumented parameter.

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 identifies the action ('Save'), the resource ('output of a deep scan'), and the target ('onto the agent'), with a parenthetical specifying the content types: company description, people, contacts. It is specific enough that an agent can distinguish it from sibling tools like scan_website_quick or save_audience, though it does not explicitly name those siblings.

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 offers no guidance on when to use this tool versus alternatives, no prerequisites (e.g., that a deep scan must already have been run), and no exclusions. The only implicit context is the phrase 'output of a deep scan,' which suggests it should be used after deep_scan_agent or preview_deep_scan, but this is left to inference.

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