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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world), so the bar is lower, and the description still adds real behavior: ranked results with canonical URLs, a match strength showing matched and missing words, and the important caveat that weak matches are background only. It does not say whether snippets are full text or whether get_paper is needed to read a hit, which is the remaining gap.

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 verb, resource and corpus inventory, then the use domains, then the scoping rule and the return behavior. The long domain list reads partly as retrieval keyword padding, but each item is a plausible user topic, so little is genuinely wasted.

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 shape need not be explained, and annotations carry the safety profile; the description covers purpose, routing, scope guidance and the weak-match caveat. The one missing piece is the handoff to siblings — it never says to use get_paper, get_technical_page or cite_paper after a hit, leaving the agent to infer the next step.

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 75% and both enum parameters are already described in the schema, so the baseline is high. The description still adds meaning beyond the schema by explaining the operational consequence of the scope value: a question about one element or system should be scoped to the technical library alone, which tells the agent how to set the parameter rather than just what its values are.

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 (search) plus the exact resource (the public Moyne Ross corpus) and enumerates its constituent parts: 49 Capital Made Physical papers, the 103-page Technical Library, the Capital Register and MR Index methodology, and a sample Capital Strategy. An agent can tell this apart from get_paper, list_papers and get_technical_page, which fetch or enumerate rather than search.

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 concrete when-to-use domains (capital planning, lifecycle and condition, obsolescence, refurbish or redevelop, energy and solar, leases and make good, due diligence, AU/UK/US markets) and an explicit narrowing rule: for a single element or system, scope technical searches to the library alone. It also states a boundary condition, 'General research: it does not assess a particular building,' which tells the agent when this tool is not the right answer.

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