Search Physical AI platforms, deployments, guides and methodology

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds behavior annotations don't cover: each result carries an evidence level, the sources behind it, explicit limitations (what is NOT published), and instructions to cite canonical_url. That is substantive, non-redundant context for a research tool, though it doesn't discuss pagination depth or ranking behavior.

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-loads the dataset scope, then filters, then result shape, then the sibling alternative — a sensible ordering. The long parenthetical enumerating robot categories costs some space but usefully concretizes scope, so most of the density earns its place.

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 7-parameter, output-schema-backed search tool with rich annotations, the description covers scope, filtering intent, result contents, citation expectations and the alternative tool. Locale and limit behavior are left entirely to the schema, which is acceptable given 100% coverage.

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 all seven parameters are already documented, and the schema is the authority on limit, locale, and enum values. The description adds only a light grouping hint ('filter by type and taxonomy ids') that maps loosely onto types/families/sectors/environments, which is marginally useful but below what the schema already provides.

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 (search) plus the exact resource (the Physical AI dataset) and enumerates its contents — platforms, deployments, guide, taxonomy, methodology — so an agent knows precisely what domain this covers. It also contrasts itself with search_all, making it distinguishable from siblings 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?

Explicit routing guidance: 'Use this for any question about robots, robotic platforms or real robotics deployments; use search_all when the question may also concern the rest of the corpus.' This names both the when and the alternative, which is exactly what an agent needs to choose between overlapping search tools.

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