extract_blocks

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered; the description adds real behavioral context on top: confidence is a model probability and null means unknown, not low, and pages_needing_vision flags pages whose text layer is missing so nothing returned for them is real content. It also discloses the page-limit behavior and the furniture default.

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-loaded with the result shape, then block fields, then the caveat, then Args; each part is useful. The block-field enumeration is long but earns its place because the output schema's field meanings are otherwise opaque; minor trimming possible but nothing is filler.

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?

Even though an output schema exists, the description explains the non-obvious field semantics (confidence nullability, bbox origin, span fields) and the pages_needing_vision caveat, which the schema cannot. For a 3-param, closed-world read tool, an agent has everything needed to call it correctly.

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 0%, so the description must carry all parameter meaning, and it does: path is the absolute path on this machine, pages is 0-based with omit-meaning-whole-document and the server limit, and include_furniture is explained with the rationale for its false default. This fully compensates for the undocumented schema.

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 and resource ('A local PDF as blocks, in reading order') with provenance per block, so the agent knows exactly what comes back. It does not contrast itself with siblings like extract_text or extract_markdown, which repeat the same 'extract from PDF' framing, so the boundary is left to inference.

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?

Usage context is implied rather than stated: 'local PDF', 'reading order', and the default exclusion of furniture give hints, and it explains the page-window and server page limit. But there is no explicit when-to-use-this-vs-extract_tables/extract_markdown guidance, which is exactly where an agent stands when choosing among the eight siblings.

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