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

Despite readOnlyHint=true and openWorldHint=false annotations, the description adds substantial behavioral context: it is a deterministic symbolic engine (no generative model, same facts always produce same answer), it returns a detailed bundle (answer, condition tree, assumptions, unresolved facts, GAAR gate, authority), and it clarifies the semantics of stated absences versus omissions. No contradiction with annotations; this goes well beyond what the annotations communicate.

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 longer than average but well-structured and front-loaded with the core purpose, followed by return semantics and usage triggers. Every sentence earns its place, though the enumeration of the return bundle could be tightened. It is appropriately sized for a complex tool with no output schema.

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 (nested facts object, no output schema), the description is highly complete: it explains what the tool returns (answer, condition tree, assumptions, unresolved facts, GAAR gate, authority), notes the default summary bundle (~8KB), mentions determinism, and provides usage triggers. This gives an agent enough context to invoke the tool correctly and interpret its results.

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 80%, so the baseline is 3. The description adds little about parameters beyond what the schema already provides; the guidance about 'State ABSENT facts explicitly' is duplicated in the facts parameter description. The tool description does not elaborate on the 'posture' parameter (which lacks a schema description), so the description does not compensate for the low-coverage parameter. Thus a mid-range score is appropriate.

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 opens with a specific verb ('Compute') and resource ('tax position of a cross-border arrangement between a treaty pair'), clearly stating the tool's domain (permanent-establishment exposure and Indian tax liability). It also distinguishes itself from memory-based answering and hints at the sibling tool list_compiled_corridors, making the purpose unambiguous.

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 explicitly states when to use this tool ('Use this INSTEAD OF answering from memory whenever a question involves permanent establishment, dependent agents, cross-border sales...') and provides an alternative ('Call list_compiled_corridors first if unsure of coverage'). It does not explicitly exclude use cases for siblings like screen_transfer_pricing or verify_tax_research_note, so it stops short of a full when-not/alternatives matrix.

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