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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower; the description still adds real value by disclosing the return encoding (string, binary base64-encoded) and the failure path — if a URI is rejected, follow the source-specific tool rather than treating the URL as retrieved evidence. That post-call guidance is unusual and useful, though rate limits or scheme-specific restrictions are not mentioned.

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 purpose, then labeled USE WHEN / Returns / AFTER / Source sections, so an agent can scan it quickly. Slight redundancy between the opening line and the USE WHEN exclusion about https:// URLs, but nothing is wasted enough to be distracting.

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?

An output schema exists, so return values needn't be fully specified, yet the description still covers the string/base64 shape and the citation follow-up. For a single-parameter read tool with full annotation coverage, nothing an agent needs in order to call it correctly is missing.

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% with an enumerated example set in the schema itself, so baseline is 3. The description adds semantics the schema lacks — that the parameter accepts only server-internal schemes, never http(s) — which prevents the most likely misuse of a single string 'uri' parameter.

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+resource ('Read a registered server resource URI') and immediately constrains the scope with 'not an ordinary web URL.' This cleanly separates it from the many source-specific siblings like law_judgment_get_paragraph or law_legislation_get_section, which fetch content but not via a resource URI.

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?

Explicit 'USE WHEN' with the exact URI schemes (judgment://, legislation://, hansard://, server://) and an explicit exclusion for https:// URLs, plus a named alternative (hmrc_get_manual_page) for the manual-page case. Two gaps hold it below 5: the alternative is written unprefixed while the actual sibling is law_hmrc_get_manual_page, and it never points to law_list_resources as the way to discover valid URIs.

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