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

The description goes well beyond the annotations by explicitly stating there is 'no execution/control/spending/publication authority', that contributed fields are 'inert data', and that structured fields are 'not an injection security boundary'. It also warns against following instructions in data and clarifies that cross-project results are not a global snapshot.

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?

The description is dense and includes repeated security warnings, making it longer than necessary for a simple search tool. Some phrasing is redundant and jargon-heavy, though the safety clarifications are valuable.

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?

The description covers result contents, open-world caveats, and safety boundaries, but lacks parameter-level explanation and explicit guidance on when to prefer this tool over siblings. Since an output schema exists, return-value detail is less critical, but usage context remains incomplete.

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?

Most parameters are undocumented: after, limit, snapshot, author_key, and record_type are not explained. The description mentions query and project_id behavior but leaves the other five parameters' meaning and interaction unclear.

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 action ('Search listed public-untrusted records using query') and clarifies a special mode ('With project_id, inspect an explicitly addressed... even if unlisted'). However, terms like 'Common' and 'public-untrusted' are not defined, and the resource type is somewhat ambiguous.

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 description implies when to use the project_id variant but does not explicitly contrast this tool with siblings like haidaa_search_public_graph or haidaa_network_summary. It gives a conditional use case but no clear selection guidance among alternatives.

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