Structured Extract

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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds that it costs 2 MESH/call and is powered by api.meshtool.ai, which is useful cost/source context. However, it doesn't disclose error behaviors, rate limits, or what happens with unsupported JSON shapes — the annotations already cover the safety profile, so the addition of cost info gives modest value.

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 compact sentence plus a compact 'Input:' note with the parameter list and cost. It front-loads the core purpose and packs cost, source, and input structure efficiently. Minor noise from '(a tool · extraction)' trailing label, but overall efficient.

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 tool's purpose is simple (text + shape in, structured data out), annotations cover the safety profile, and schema coverage is full. The description covers the input contract and cost. Without an output schema, the description could clarify return behavior more, but for a straightforward extraction tool with 100% schema coverage, it is reasonably complete.

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 description coverage is 100%, with both 'text' and 'shape' parameters documented in the schema. The description adds that text is 'string' and shape is 'object' with the expected semantic meaning, but doesn't add beyond what the schema provides. Given full schema coverage, baseline 3 is appropriate.

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 states the tool extracts structured data out of free text into a user-defined JSON shape, mentioning classification, field extraction, and scoring. This clearly states the verb (extract/pull), resource (free text), and output (JSON shape). It distinguishes broadly from sibling tools like agent-memory or task-analysis, though it doesn't explicitly contrast with them.

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 clearly shows it's for pulling structured data out of free text and lists the required inputs (text and shape). It implies usage for text-to-structured-data conversions but doesn't explicitly state when NOT to use it or name alternative tools for different scenarios (e.g., classification vs extraction vs scoring). No exclusions or alternatives are given.

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