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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile needs no restating. What the description adds beyond them is result-shape behavior: the tier definitions, the absence of a numeric relevance score, the partial-match fallback with a 'matched' list, and the note that withheld/withdrawn documents are simply absent. That is substantive extra context.

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 purpose and trigger before the longer tier taxonomy. The tier block is lengthy but justified because there is no output schema to explain result structure; nothing reads as filler, though the passage could be tightened slightly.

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?

Nine parameters, no output schema, and no enum constraints, yet the description covers ranking tiers, match explanation fields, paging context, partial-match behavior, scope exclusions, and coverage limits. An agent has everything needed to call it and interpret the result correctly.

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 parameter documentation is already carried by the schema. The description still contributes semantics the schema does not: filters use the website's own facet vocabulary, and search covers extracted full text as well as catalogue records, which tells the agent what 'query' actually matches against.

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?

Says precisely what it does: searches the archive's full extracted text plus catalogue records, with named filter dimensions (collection, entity, content type, island, year). The one gap is that it never distinguishes itself from the sibling 'search' tool, leaving the agent to infer the split from the filter list alone.

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 positive trigger ('when a question needs narrowing, paging, or the reason each document matched') and an explicit exclusion with a pointer elsewhere ('newspapers ... on its separate newspaper connector'). It stops short of routing among the sibling tools search, fetch, and get_document_text, which the agent must guess at.

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