Place desk

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

Beyond readOnlyHint, it discloses that the unlinked tail is a labelled, never-merged substring match, that name lookups fail without the gazetteer dump while numeric ids still count holdings, that coordinates are display-only with no math, and that attribution/license fields must be preserved. These are exactly the non-obvious behaviors an agent needs before quoting results.

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?

Purpose and scope are front-loaded and every clause carries operational information; there is no filler sentence. It is dense single-paragraph prose with heavy parenthetical nesting ("the catalog side needs no dump, the card is just fact-less") that slightly hurts scannability but not comprehension.

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?

With no output schema, the description still characterizes the return card (facts, per-source aggregate counts, honest unlinked tail, attribution block) and the degraded-mode behavior. For a one-parameter read tool, nothing an agent needs to call it or interpret the response 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%, so baseline is 3, but the description genuinely adds meaning: it documents NAMESPACED refs (tm:2810, cigs:GIR) that the schema never mentions, the case-insensitivity of exact titles, and the hard no-fuzzy-matching rule. Only the URL/id equivalence was already in the schema.

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?

The description states a specific resource and scope: one ancient place resolved via the local Pleiades dump or multi-gazetteer index, plus per-source holdings at that place. It explicitly distinguishes the aggregate output from the sibling tools that return texts (nabu_search/nabu_show), so an agent can route correctly without opening schemas.

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?

It gives clear triggering context and names alternatives for the text-reading side ("read the texts with nabu_search/nabu_show"), plus concrete matching rules (exact title only, no fuzzy, homonyms yield one card each). It does not contrast against the other place/no-place siblings such as nabu_concord or nabu_links, so the exclusion set is incomplete but the core routing is clear.

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