Item Search

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

No annotations are provided, so the description carries the full burden, and it does disclose real behavior: returns summaries not full content, default project/workspace scoping with no cross-project leakage, everywhere=True for global search, relevance-first ranking, accent/plural tolerance, and include_inactive surfacing superseded/obsolete/expired ephemeral items. It stops short of stating read-only guarantees or pagination/rate behavior, but the behavioral disclosure is rich.

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, then bolded Use/Returns/Example/Notes sections that scan quickly. Slightly dense in the Notes paragraph but no redundant 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 10-parameter tool with zero schema coverage and no annotations, several filters (types, domain, memory_classes, connection_id) remain undocumented. The return-field list is redundant given an output schema exists, while the genuinely useful undocumented parameters are not covered, leaving the definition only partially complete.

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 0% across 10 parameters, yet the description explains the semantics of key ones: project/workspace defaulting, everywhere, include_inactive, and query/limit (with a limit=5 example). It leaves types, domain, memory_classes, and connection_id completely unexplained, so it only partly compensates for the coverage gap.

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 clear verb+resource (text search over stored items) and immediately draws a boundary relative to the sibling item_get by saying it "devolve resumos, nunca o conteúdo completo." An agent can tell it is a search/retrieval tool and not a fetch-full-content tool, though item_get is never named explicitly.

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 "Use quando" block gives a concrete trigger (looking for something that may already be stored: decision, gotcha, procedure). It does not name alternatives or explicit exclusions, but the summary-only constraint implicitly routes full-content needs elsewhere.

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