access extract

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) by disclosing that the file is uploaded via RapidAPI to a NAS service, consumes plan allowance, is single-shot with no automatic retries, leaves originals untouched, and writes verified results as new local files. It also flags returned artifacts as untrusted data, a genuine prompt-injection warning.

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?

Front-loaded with purpose and limits, then prerequisites, network/cost behavior, and a safety note. Every sentence carries a distinct, actionable fact (size cap, consent, plan consumption, no retries, non-destructive output) with no 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?

With no output schema, the description still tells the agent what comes back (typed JSON or a CSV ZIP, saved as new local files) and covers cost, network egress, retry semantics, and data trustworthiness. Nothing needed to call this correctly is missing.

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 coverage is only 33% (only 'consent' is documented inline), but the description compensates: it explains the accepted file type and size ceiling for 'file' and the typed JSON vs CSV-ZIP outcomes for 'format', and restates the consent gate. It does not spell out accepted path syntax or whether 'file' may be a URL, leaving a small gap.

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 and resource ('Export supported scalar tables from a local MDB/ACCDB snapshot') plus hard scope limits (40 MiB, typed JSON or CSV ZIP). It also names what it is not ('Does not migrate forms, macros, saved queries or linked data'), so an agent can separate it from any inspection/preview sibling without reading schemas.

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?

Clear preconditions and exclusions: local MDB/ACCDB snapshot, ≤40 MiB, consent:true, and an explicit when-not list (forms, macros, saved queries, linked data). It does not name an alternative tool or say what to do when the input is a remote/live database, so it stops short of full routing guidance.

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