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

Description significantly enriches annotations: 'weekly-refresh feed' reveals staleness cadence, 'replaying the same since gives the same answer' translates idempotentHint into a concrete guarantee, and the note about withdrawals being absent is a critical limitation. No contradiction with readOnlyHint/idempotentHint was found.

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 description is well-structured, front-loads the core purpose, and uses the note to present the critical limitation. Every sentence contributes: purpose, input format, output relation, and semantic caveat. No fluff or redundant restatement.

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 simple three-parameter tool with no output schema, the description is unusually complete. It explains what the tool returns (same rows as mhra_search plus cutoff), the refresh cadence, the replay semantics, and the key limitation about withdrawals. The annotations cover safety and idempotency, so nothing essential 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 description coverage is 100%, so the baseline is 3. The description adds a concrete example of the `since` format and mentions the 'cutoff that was applied' in the output, but does not add additional parameter-specific semantics beyond the schema. It stays at the sufficient baseline.

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?

Description states a specific action and resource: 'MHRA documents added or revised since a date, newest first — the weekly-refresh feed.' It clearly names the entity, the operation, and the ordering. It also distinguishes itself from siblings by explicitly referencing mhra_search and noting it returns the same rows plus the cutoff.

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?

The description gives clear context for when to use the tool: when you need documents added or revised since a date, using an ISO date. It names mhra_search as a comparison point ('same rows as mhra_search plus the cutoff'), implying mhra_search for general search. However, it does not explicitly state when not to use this tool or contrast it with mhra_snapshot or other siblings.

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