ag_table_markdown_extract

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

With no annotations, the description carries the full burden and does well: it states determinism, fixture verification, guest rate limiting, and the Guild-signed provenance envelope. This sets strong expectations about behavior and output wrapping.

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 compact, with no redundant content, and the key details (input format, output shape, behavioral guarantees) are front-loaded. Every sentence 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?

Combined with the provided output schema and nested payload schema, the description covers what the tool does, what it returns, and when to use it. No important operational detail is missing for a deterministic extraction utility.

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?

The input schema only shows a generic payload object plus optional api_key; the description adds the required nested markdown property with maxLength 60000 and explains api_key as the way to get member budget. This materially improves parameter understanding.

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 opens with a specific verb-object pair ('Extract structured tables from markdown text') and immediately scopes the input to GitHub-style pipe tables and the output to columns+rows. This makes it easy to distinguish from JSON/CSV siblings.

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?

It gives an explicit use case ('model output or docs before downstream structured processing') and limits input to GitHub-style pipe tables. It does not name an alternative for non-pipe-table or CSV inputs, but the format scoping is clear enough for typical selection.

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