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

With no annotations provided, the description carries the full burden. It discloses case-insensitive matching, substring containment (via 'contain'), and a result cap of 50. However, it does not mention result ordering, pagination, whether all columns are searched (though 'cells' implies all), or the exact return format. These gaps keep it from being fully transparent, though core behaviors are 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?

The description is a single, concise sentence that front-loads the core action (rows containing query) and includes key modifiers (case-insensitive, up to 50). There is zero waste; every element adds value. It is well-structured and immediately scannable.

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?

The description is adequate for a simple search tool but missing some contextual details: it does not specify the return format (full row objects vs IDs), result ordering, or whether there is a default limit if the limit parameter is omitted. Given the lack of an output schema and annotations, these details would help an agent invoke it correctly, but the core functionality is clear enough for basic use.

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 50%: the query parameter has a description in the schema, while limit has only type and constraints. The description adds no parameter-specific meaning beyond the schema, but the schema itself adequately explains limit via min/max. The description's 'up to 50' reinforces the limit but doesn't clarify default behavior. Since coverage is moderate, a 3 is fair.

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 clearly states that the tool returns rows of a specific dataset whose cells contain the query, with case-insensitivity and a limit of 50. It uses a specific verb (implicitly 'search') and resource (Mashzo dataset), and it is distinct from siblings like dataset_row (single row) or dataset_stats (statistics). However, it does not explicitly name sibling alternatives to differentiate, so a 4 is appropriate.

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?

The description implies usage: if you need to find rows containing specific text across any cell, use this tool. It does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives. The context is clear but lacks explicit exclusions or comparisons with sibling tools.

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