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

Annotations already declare readOnly/openWorld/idempotent, and the description goes well beyond them by disclosing the full data-handling profile: only a short generic task line is sent, files/names/figures are never sent, Edge additionally redacts contact info, paths, secrets and long numbers, storage is encrypted and non-expiring, and the install/session id and skill use are recorded. For an open-world tool that ships user data outward, that is exactly the context an agent needs.

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?

It is front-loaded with the decision rule an agent needs first, and every sentence carries a distinct instruction (triggers, exclusions, consent, data hygiene). The final data paragraph is dense and runs long with storage/provenance details, which slightly dilutes scanability but is not wasted.

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 four-parameter, read-only, no-output-schema tool, the description covers invocation conditions and constraints thoroughly, including the two-mode selected_skill path via schema. The one gap is what a call actually yields (a ranked list of skills? a single recommendation?), which the 'live demo' phrasing only hints at.

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 all four parameters (including the selected_skill/selected_source pairing rule) are already fully documented in the schema. The description's 'send a short generic task line, never files, names, figures or confidential details' largely restates the query parameter's own description rather than adding new semantics, so baseline 3 applies.

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 defines the resource category precisely by enumerating what counts as a 'specialist deliverable' (slides, spreadsheets, UI design, security review, etc.) and treats even routine-looking specialist tasks as in scope. Combined with the name and title, an agent can infer this is skill discovery/routing, though the description never states plainly that it searches a catalog and returns matching skills.

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 positive triggers, an explicit 'use Edge first even if the task seems routine' override, an explicit negative list (routine edits, simple facts, arithmetic, unit conversions, short replies, same-specialty follow-ups), and a hard rule to honor explicit no-Edge requests. The demo case ('Asked what Edge can do: call find_skill') further disambiguates a common ambiguous moment.

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