read_document

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavior beyond that: the dual-mode key semantics and the fact that oversized values are refused and reported with their size.

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 tight sentences, front-loaded with the tool's role, then the two modes, then the routing rule and the size-limit caveat. Every sentence earns its place; no 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?

With no output schema, the description still explains all three return shapes (key listing with type/size, stored value, refusal-with-size) and the fallback context. An agent has everything needed to call it correctly and interpret the result.

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 for the single `key` parameter, and it fully does so: absent `key` means list top-level keys with type and size; present `key` means return that value as stored. This is exactly the semantic the bare schema lacks.

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 (reads the raw profile document), and precisely describes two distinct modes: no `key` lists top-level keys with type/size, with `key` returns that value as stored. An agent can distinguish it from read_profile and other dedicated read_* siblings without opening the schema.

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?

"Escape hatch" plus "Prefer the dedicated tools; use this for data they do not cover" gives an explicit when-not-to-use rule and names the alternative class of tools. Nothing about routing is left to inference.

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