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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds value with 'No auth required,' the source ('SA National Treasury MFMA data portal'), and data scope ('2010-2024 for all 257 municipalities'). It also discloses the return shape (year, opinion label, PDF URL). These go beyond the annotations without contradicting them.

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 well-organized paragraph of about 120 words. Each sentence adds value: action, codes, return fields, filters, coverage, use cases, auth, and source. It is front-loaded with the core purpose and avoids superfluous content, making it efficient for an agent to parse.

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?

With an output schema present, the description need not list all return fields, but it still mentions the key ones (year, opinion label, PDF URL). It covers the data range, intended use cases, authentication requirements, and source. All three optional parameters are described in the schema, and the description provides sufficient context for correct invocation without gaps.

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 100%, so each parameter (year, limit, demarcation_code) already has detailed descriptions with examples and constraints. The tool description only paraphrases 'Filter by demarcation code and/or year' and does not add new meaning beyond the schema. Since the schema does the heavy lifting, the baseline of 3 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 clearly states 'Get Auditor-General of South Africa (AGSA) audit outcomes for municipalities,' specifying both the verb and the resource. It distinguishes from siblings like samuni.finance.income_expenditure and samuni.reference.municipalities by focusing on audit opinions, and it details the opinion codes and return fields. The agent can confidently select this tool for audit outcome data.

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 provides useful context on when to use the tool ('transparency reporting, credit risk assessment, and governance analysis') and mentions filtering by demarcation code or year. However, it does not explicitly state when not to use it or how it compares to alternatives like samuni.finance.income_expenditure. It gives clear context but lacks explicit exclusions or alternative routing.

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