list_milestones

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds one useful behavioral detail beyond the annotations — that the result includes an issue count per milestone — but it says nothing about pagination behavior, default state filtering, or response characteristics. Not contradictory, just thin.

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 front-loaded sentence with zero wasted words. The verb, resource, and key return-value detail ('count of issues') all appear in the first line. It is appropriately compact for a simple list operation, though it borders on too sparse to add much value.

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 a simple read-only list operation with an output schema (return values documented elsewhere) and safety annotations, so the baseline burden is low. Still, the definition omits practical call context: no mention of the default state ('open'), pagination semantics, or which sibling to use for related milestone operations. Adequate but not complete.

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 only 40% (only 'state' and 'per_page' are documented), which falls below the 50% threshold, so the description must compensate for the undocumented params (page, repo_owner, repo_name). The description does not compensate at all — it merely implies 'a repository' without explaining any parameter semantics. The two documented params are the most meaningful, which prevents a score of 1, but the gap remains.

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 states a specific verb ('Lists') and a clear resource ('a repository's milestones'), so an agent can tell what the tool does and distinguish it from create_milestone, update_milestone, and set_issue_milestone by verb. It also adds a distinguishing detail (count of issues in each milestone). However, it never explicitly names sibling alternatives, so differentiation is implicit rather than stated.

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 context is only implied through the verb 'Lists', suggesting a read/view operation rather than creation or modification. There is no explicit guidance on when to prefer this tool over siblings like list_releases, list_tags, or list_repo_labels, and no 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.