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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, so safety is covered. The description adds real behavioral context beyond that: what each mode actually searches, the default full-archive scope, and the narrowing effect of window/place. It stops short of describing result ordering, result shape, or cost/rate behavior, which no output schema covers either.

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?

Three tight sentences, front-loaded with the core verb and the mode split, then scope, then the sibling hand-off. The clause about reading the whole archive and optionally limiting to one place lightly restates the window/place defaults already in the schema, which is the only small redundancy.

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 6-parameter search tool with rich annotations, the description covers modes, default scope, narrowing options and an alternative tool. With no output schema, the one remaining gap is what a result actually looks like (a story vs. thread vs. location, ordering, per-kind limits), but nothing required for a correct call 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 100% so the baseline is 3, but the description adds meaning the schema does not: it explains what 'semantic' does relative to 'keyword' with an example query, enumerates the entity kinds keyword mode reaches, and clarifies the window default in behavioral terms ('reads the whole archive'). It does not elaborate on limit or place syntax beyond what the schema already says.

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+resource ('Search Mappit') and immediately disambiguates the two operating modes with concrete scope for each (keyword covers stories, storylines, places, businesses, pins, collections; semantic covers only stories and storylines). It also names a sibling, whats_happening, so an agent can tell the two apart without opening a schema.

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?

Gives explicit mode-selection guidance with a worked example ('tenants organizing against rent increases') for when semantic is the right choice, states the default behavior (whole archive unless a window is given), and routes to the alternative tool for a specific need: 'For the latest news in a place, use whats_happening.'

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