get_vat_report

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

There are no annotations, and the description does not disclose any behavioral traits such as read-only status, permissions, or response format. The noun-phrase description ('Rapport de déclaration TVA...') does not even explicitly state that the tool returns a report, leaving the agent to infer from the name. This is a significant gap for a tool with no 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 compact sentence with no redundant information. It is front-loaded with the key concept (VAT declaration report) and includes the main differentiator (collected vs deductible). This is appropriately sized.

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 tool is relatively simple (two parameters, no output schema), and the description covers the core purpose. However, it omits behavioral details like read-only nature, exact return contents, and any conditions; these are not covered by annotations or output schema. It is minimally viable but has clear gaps, especially given the lack of annotations.

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?

The schema already documents month as 'Mois 1-12 (si vide = année entière)', but year has no description. The description only mentions 'pour une période' without explaining the required/optional nature of parameters or their formats. It fails to compensate for the missing year description, so the description adds no semantic value beyond the schema.

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 identifies the tool as producing a VAT declaration report for a given period, with a breakdown between collected and deductible VAT ('collectée vs déductible'). It distinguishes from sibling tools like get_trial_balance by focusing specifically on VAT reporting. However, it lacks an explicit verb like 'retrieves' or 'returns', relying on the tool name 'get'.

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?

No guidance is provided on when to use this tool versus alternative accounting/reporting tools. It does not mention any exclusions, prerequisites, or comparisons with siblings such as get_trial_balance or get_financial_summary. The description only names the report without situational context.

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