search_icons

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

With no annotations, the description carries the full burden and does well: it declares 'Does not modify the board', explains the `path`-optional-when-app-open precondition, and discloses match semantics ('every word of `query` must match (case-insensitive) the icon name, its set or its group') plus the `truncated` signal for overflow. It stops short of describing result shape beyond ids or any performance/rate behavior, but the safety and matching profile is well covered.

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 the action and scale, and every clause contributes (matching rule, return value, alternatives, read-only guarantee). The parenthetical icon enumeration is the only mildly verbose element, though it does help an agent judge coverage.

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 read-only search tool with no annotations and no output schema, the description covers what matters: what is searched, how matching works, what is returned (ids), how truncation is signalled, and the `path` precondition. Enough to invoke correctly without opening the schema.

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 100%, so baseline is 3, but the description adds real meaning: the AND-of-all-words, case-insensitive matching against name/set/group is not in the schema, and it frames `group`/`set` as narrowing filters and `limit`/`truncated` as interacting. That is genuine semantic value on top of documented params.

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?

Specific verb + resource: 'Searches the built-in icon library ... by keywords', with scope quantified (~28,800 icons) and content types enumerated (AWS, Azure, Kubernetes, brands, UI symbols). It is clearly distinguished from list_icon_groups (browsing) and add_icon (consuming the returned ids).

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?

Explicitly routes the agent to siblings: 'Returns ids to give to add_icon' and 'Use list_icon_groups to see what the library contains'. Also gives a narrowing strategy — '`group` / `set` to narrow a broad search' — for the common case of an over-broad query.

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