diana_manual_read

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds useful behaviour beyond that: page-name normalization (accepts "Theoryse738" as well as the full path), the fact that find starts reading shortly 'before' the match rather than at it, and the next_offset continuation pattern. Return-format detail is left to the output schema, which exists.

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 lead sentence front-loads purpose and provenance before the parameter list, and every line carries information. The "Args:" block duplicates structure the schema should normally own, but given 0% schema coverage that repetition is functional rather than wasteful.

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?

For a paging read tool with an output schema supplying next_offset, the description covers everything needed to call it correctly: page identification, position seeking, continuation, and size control. Nothing an agent would need to infer incorrectly is left out.

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 0%, so the description carries the full burden, and it does: page is given with a concrete path example plus the accepted shorthand, find is explained with realistic examples ("LINPAG", "I.1.1.2"), offset is tied to next_offset from a prior call, and max_chars is identified as a character budget. This is exactly the compensation the low coverage requires.

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 ("Read a page of the DIANA user's manual as text") and orients it against the sibling diana_manual_search by noting pages typically come from those results. It stops short of an explicit contrast statement (e.g. what search does that read does not), but an agent can still separate the two.

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?

Implies the search-then-read workflow and gives concrete operational guidance for the offset parameter ("use next_offset of a previous call to continue") and for resuming reads. It lacks any explicit when-not guidance or statement about page-size tradeoffs, so a 4 rather than a 5.

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