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

Annotations already cover the read-only/non-destructive profile, and the description adds real behavioural detail beyond them: result ordering ('newest first and the ones still going on top'), the default scoping precedence, and the fact that 'open' expands to two underlying states. It does not cover pagination behaviour beyond the limit field, but that is minor for a read tool with annotations already in place.

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?

Dense and largely waste-free, but the prose is convoluted with em-dash asides and the actionable ordering/state information is buried mid-sentence rather than front-loaded. The opening clause spends words on a metaphor before saying what the tool returns.

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 four-parameter read tool with no output schema, the description covers scoping, precedence, ordering, state values and the shape of returned records. The only gap is what happens with pagination/limits when many computations exist, which the schema's limit field partially covers.

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%, so the baseline is 3, but the description goes further: it enumerates the concrete state values (queued, running, done, failed, cancelled, lost) where the schema defines no enum and only hints at 'open', and it explains that 'key' overrides 'projectKey'. It also clarifies what 'open' means in terms of two states grouped together.

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 makes clear this returns the CI/computation records attached to issues, including state, progress, commit, repository, job page and output. It distinguishes the two scoping modes ('key' = one issue's, 'projectKey' = the project's) so an agent can tell how this differs from a generic issue listing. The opening phrase 'the computations issues rest on' is abstract and the verb 'list' is only implied by the name, which keeps it out of 5 territory.

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?

Explicitly recommends state 'open' as 'the first thing to ask after a lost session instead of reading status comments', which is a concrete when-to-use plus a named alternative behaviour. It also states 'key' takes precedence over 'projectKey'. No explicit 'when-not-to-use' or mention of the sibling delete_computation, but the routing guidance is strong.

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