filterNetworkTokens

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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds that it is 'Read-only and keyless' and explains pagination mechanics. However, it does not mention potential errors, rate limits, or data freshness, which would be helpful but are not required given annotations.

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 a single paragraph but front-loads the core purpose and usage. It covers many details without being verbose. Slight improvement could be bulletizing filter groups, but it remains efficient.

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?

Given the tool's complexity (17 parameters, sibling scope, output schema exists), the description covers all essential aspects: intent, when to use, parameter semantics, aliases, pagination, and required rationale field. It is fully sufficient for an agent to select and invoke correctly.

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%, baseline 3. The description adds value by noting filters are AND-combined, explaining aliases (sort_by/order_by, sort_dir/sort), and grouping optional filters. It goes beyond the schema descriptions.

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 clearly states it retrieves tokens on one network matching numeric thresholds, specifies the return structure (results, has_next_page, next_cursor), and distinguishes itself from the sibling tool getTopTokens by indicating when to use each. It provides specific examples like 'tokens with FDV over $10M on Base'.

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?

Explicitly tells when to choose this tool over getTopTokens ('when the user gives numeric constraints or a time window') and provides concrete use case examples. This is unambiguous guidance.

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