gc_timing

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does state 'read-only' upfront, which is good. However, it doesn't disclose behaviors like what happens on empty results, date range validation, label matching behavior, or database accessibility/unavailability handling. For a DB query tool with zero annotations, more behavioral detail is needed.

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 compact and front-loaded with the key facts (read-only, source, actions). The action list is efficiently packed into one line. Efficient use of space without redundancy.

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?

For a database query tool with 4 parameters, an enum action field, and no output schema, the description is fairly minimal. It identifies the actions but doesn't describe expected return shapes for any action, no examples of parameters, and no indication of how labels or date ranges affect results. It's adequate to understand what the tool does but insufficient for confidently predicting behavior for each action combination.

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% with good parameter descriptions (ISO date filters, labels for duration, action enum). The description adds a bit of value by mapping each action name to its semantic meaning (summary=project totals, duration=estimate from labels). But it doesn't elaborate on interaction between 'since'/'until' and specific actions, or which actions are compatible with which parameters.

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 read-only queries against macOS Timing.app SQLite database and lists the actions (summary, capacity, duration, hours_by_label). It identifies the resource (Timing.app database) and specific query actions, which distinguishes it from siblings. However, it doesn't fully explain what each action returns.

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 on when to use this vs alternatives, no prerequisites mentioned. It declares read-only nature but doesn't specify when to use each action or how it relates to other gc_* tools. The action names are listed but without explanation of appropriate use cases.

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