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

Annotations already declare readOnly=true, idempotent=true, destructive=false and closed-world, so the safety profile is covered. The description adds non-obvious behavioral context beyond that: only published site content is searched and private customer records are never accessed, plus the demotion/exclusion behavior of the underlying search. It omits return shape/ordering, but for a read tool the added privacy and content-policy detail is substantive.

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?

Three sentences, front-loaded with the core verb+resource, then the exclusion policy, then the privacy boundary; nothing is redundant with the title or schema. It could have spent one of those sentences on the parameters instead, but there is no filler.

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 12-parameter, all-optional search tool with no output schema, the description should say more about result shape, ordering and paging relative to the hard limit/max of 10, and about which filters are ANDed together. It covers the content-policy dimension well but leaves the mechanics of invoking a many-filter search underspecified.

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 50%: six parameters (tag, mode, scope, service, object_type, initial_state) already carry their own descriptions, while year, limit, query, location and the two area bounds do not. The description only gestures at the axis of filtering ('by locality and/or topic'), adding no format, unit, or interaction guidance (e.g. whether tag and service combine, how query differs from scope). Baseline 3 is the right ceiling given the schema does half the work and the description does not close the other half.

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 names a specific verb (search) and resource (public Oleba project/gallery realization content) and scopes it by locality/topic. It is clear what an agent gets, though it never distinguishes itself from the singular sibling get_realization or from search_site, so the agent must infer search-vs-fetch from the name 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?

It provides real selection context: generic service pages, local landing pages and price-list pages are 'intentionally demoted or excluded', which tells the agent this is not the tool for price or landing content. However, it names no alternative tool (e.g. get_realization, get_price_information) the way the calibration's top example does, so routing between siblings is still left to inference.

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