local_ask

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior on top: facts must be quote-verified verbatim against the source, unquotable facts are dropped, mode='summary' yields an explicitly unverified summary, and quality auto-escalates for negative questions or empty results. This is real information an agent cannot get from the 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?

Front-loaded with purpose, then usage, then behavioral guarantee, then parameter notes, then a safety caveat. Every sentence carries content, though the parenthetical-heavy middle becomes dense and 'so you don't have to' is pure framing.

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 5-parameter tool with an output schema and full annotation coverage, the description supplies the missing pieces: routing versus Read/Grep, trust model of returned facts, mode/quality semantics, and a decision-use caveat. Return values need not be explained since an output schema exists.

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 carries the full burden, and it does explain the two least-obvious parameters: what mode='summary' changes about trustworthiness and what unset vs. True quality means. However, max_items is never mentioned and paths/question are only implied by the examples, leaving gaps the schema does not fill.

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 concrete verb+resource+output: 'Read files or directories with a local model... get back a short answer.' It clearly distinguishes itself from Read/Grep by naming them as alternatives, but it never distinguishes itself from its actual siblings local_digest and local_edit, which is the overlap an agent must resolve.

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?

It gives explicit when-to-use with concrete triggering questions ('which routes lack auth', 'where is X handled'), names the alternative (Read/Grep) and the condition that selects this tool (need facts from large/many files but not the files themselves), and states a when-not ('Do not use for decisions... without opening the cited lines').

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