get_item_fulltext

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

With no annotations, the description carries the burden and does disclose the on-demand nature, absence of a search-index prerequisite, page-marker format, and truncation behavior with max_chars. It does not cover multi-PDF aggregation or error/permission cases, but the core side effects and result caveats are present.

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?

Four sentences front-load the core purpose and then layer parameter and behavior details without redundant filler. Each sentence adds value, so it is efficiently structured.

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?

Despite no annotations and no output schema, the description covers what the tool returns (full text with page markers), how to constrain output, and how truncation is signaled. It is slightly incomplete about the exact shape when an item has multiple PDF attachments and about failure modes, but it is enough for correct invocation.

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 descriptions are 0%, so the prose must compensate, and it does: page_start/page_end are documented as 1-indexed and inclusive, max_chars is documented as a cap with a default and truncation cue. item_key is left obvious from the tool name, but all optional parameters receive meaning beyond the 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?

The description uses a specific action verb ('Extract') and names the exact resource ('an item's PDF attachment(s)'), and it adds page-marker behavior that distinguishes it from metadata/notes/search siblings. An agent can confidently choose this over get_item, get_item_notes, or get_item_annotations.

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 explains when a page range is useful and clarifies that extraction is on-demand and does not depend on the search index, which routes usage away from rebuild_search_index/search_library. It does not explicitly name alternative tools for metadata or notes, but the context is clear enough.

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