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

Annotations already declare readOnly, idempotent, openWorld. The description adds the behavioral fact that it returns multiple candidates rather than a single answer, and that disambiguation is the caller's responsibility — useful context beyond structured data. It does not cover ranking or what happens on zero matches.

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 sentences, front-loaded with the core action and return shape, then downstream routing, then the disambiguation tip. No filler and nothing repeated from the schema.

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?

No output schema exists, but the description compensates by describing the return ('candidates with name and place type') and showing example output mappings. For a 4-parameter lookup tool this leaves nothing an agent needs 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. The description goes further by explaining the disambiguation role of place_type with real ambiguous-name examples (Paris, Georgia), giving semantic motivation the schema's terse type list does not.

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: finding a Data Commons place id (dcid) for a place name, with concrete example mappings ('California' -> geoId/06, 'India' -> country/IND). It clearly distinguishes itself from the entity-resolution siblings by producing a dcid rather than a general entity profile.

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 downstream: 'Use the dcid with datacommons_observation or datacommons_child_places.' Also states when to narrow with place_type (ambiguous names like Paris, Georgia), which is actionable when-to-use guidance absent from most definitions.

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