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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint/destructiveHint=false, so the safety profile is covered; the description still adds genuinely useful behavioral context beyond them — the company-selected repository restriction and the caveat that closing an issue does not resolve the customer case. It stops short of describing pagination, missing-issue behavior, or what the permission check returns.

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?

Three short sentences, front-loaded with the action and followed by scope then caveat — no filler. The 'X, or Y' construction packs two modes into one sentence and reads slightly ambiguously, costing it a perfect score.

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 should clarify what comes back from a permission check versus an issue read, and it does neither. Combined with four parameters at 0% schema description coverage, an agent can form a rough call but cannot predict the response shape or the role of source_id.

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 0% across four parameters, so the description carries the full burden, and it only documents one: 'number' (implicitly optional, selecting read mode over permission-check mode). The meaning of source_id, environment, and company — beyond a vague 'company-selected repositories' — is explained nowhere, leaving an agent to guess at the UUID identifiers.

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?

Names specific verbs and resources ('check issue permission and repository visibility', 'read one original GitHub issue by number') and qualifies the resource as an 'original' GitHub issue, which implies a meaningful distinction from mirrored/imported data. It does not, however, contrast itself with plausible siblings such as summer_github_sources_read or summer_github_repositories_list, so an agent gets the what but not the which-one.

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 clause 'Restricted to company-selected repositories' gives a real applicability constraint, and the dual phrasing implies the permission/visibility check is what happens when no issue number is supplied. But the when-to-use versus alternatives is left implicit — nothing says to prefer summer_cases_get for case detail or summer_github_sources_read for source configuration.

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