Registro de auditoria

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds real behavioral value by disclosing coverage of failed attempts and the 'newest first' ordering. It does not mention pagination limits, retention window, or storage location details ('local' is stated but not explained relative to the remote Aspa account).

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?

A single front-loaded sentence delivers scope, coverage, and ordering with no filler. Every clause (categories, failed attempts, newest first) carries distinct information.

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?

There is no output schema, so the description must characterize the return value, and it only says entries are newest first and include failures — the fields of an entry are never described. For a read-only tool with annotations covering safety, the remaining gap is the shape of results, which an agent would need to interpret output 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 75%, with limit, since, and contact already documented in the schema, so the baseline of 3 applies. The description adds indirect value by listing action families in prose, which loosely maps to the undocumented 'action' enum values, but it never explains the enum's Portuguese labels, the interaction between since and limit, or whether contact filtering matches partial names.

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 names a specific verb and resource ('Read the local audit log') and scopes it precisely ('of every change made in Aspa through this server'), enumerating the covered categories (messages, templates, attachments, transfers, snoozes, conclusions, reopenings, renames) plus failed attempts. No sibling tool in the list is an audit-log reader, so the agent can distinguish this from aspa_statistics or aspa_list_concluded without inspecting schemas.

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 intent to review change history is implied by the enumeration of recorded actions, but there is no explicit when-to-use or when-not statement and no named alternative (e.g., versus aspa_statistics for aggregate counts). The agent must infer the use case from the scope sentence alone.

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