get_sidebar_counts

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

With no annotations, the description carries the full burden and does well: it discloses caller-only scoping, the required conversations:read permission, and a non-obvious behavioral trait — per-view counts are scan-capped at 100 (UI renders 99+). It omits the concrete response shape, but most safety/scope concerns are covered.

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 scoping and count list are front-loaded and earn their place, but the first line merely restates the title, and the raw method/path and 'Tags: Conversations' lines are low-value metadata noise for an agent choosing a tool.

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 zero-parameter read tool with no output schema and no annotations, the description covers purpose, scope, permission requirement, and a subtle cap behavior. Only the concrete field names of the returned counts are left unspecified.

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 tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate and it does not mislead about inputs.

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?

States a specific verb+resource (sidebar counts) and enumerates exactly which counts are returned: assigned, mentioned, unassigned, all, plus per-view counts for personal and team-shared views. It does not explicitly distinguish itself from the sibling overview_counts, so an agent must infer the difference.

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?

Usage is implied by 'inbox sidebar badges of the caller' — a caller-scoped badge endpoint — but there is no explicit when-to-use statement, no condition distinguishing it from overview_counts or get_assigned_conversations, and no exclusions.

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