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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral facts: it is 'not metered' and returns object_unavailable instead of a body for historical non-authorable kinds. It also flags the 'authorized' scoping constraint. Missing only latency/pagination-style details, which the output schema may cover.

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 return payload, then the selection rule, then edge-case behavior. Dense and purposeful, though the gloss on content_hash ('the document's own name: computed from its canonical content, identical wherever the document travels') is slightly verbose for the value it adds.

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 3-parameter read tool with full schema coverage and an output schema, everything an agent needs is present: how to select the record, which identifier to prefer, what the body contains, and what happens for non-authorable kinds. Return-value detail is correctly delegated to the output schema.

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 100%, so baseline is 3, but the description adds real meaning beyond it: declaration_id is characterized as a workspace-local, stable id and content_hash as the document's own canonical name that is identical wherever the document travels. That portability framing is not in the schema's terse 'Portable content hash' text.

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 with precise scope: returns one authorized declaration's canonical body plus its admission and application history. The singular 'one' plus the explicit body/history payload separates it from list_declarations without needing to name the sibling.

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?

Gives a clear selection rule ('exactly one of declaration_id or content_hash') and explains the failure mode for historical kinds (object_unavailable). It does not explicitly state when to prefer this over list_declarations or open_standard_document, so it stops short of naming alternatives.

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