CI logs

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered; the description still adds real value by disclosing truncation semantics (tail only, per-entry caps, dropped_lines/dropped_bytes), cost ("1 download", in-memory parsing) and batch-safety. It stops short of mentioning credentials required for private repos or failure behavior when a run/job id is wrong — the main remaining gap for a networked read tool.

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?

Front-loaded with the verb and the crucial caveat (tail, not whole log), then organized into Use/Avoid/Speed/Output/Batch-safe labels that are scannable at a glance. No sentence is filler; the Output line is valuable given there is no output schema.

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 read-only, open-world tool with no output schema, the description carries the full return-value burden and does so concretely (ci_logs fields, entries[], text tail, truncated/dropped counters). All six parameters are documented in the schema and the description adds selection guidance, so an agent has enough to call it correctly on the first try.

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; the description goes beyond it by tying parameters to intent — job_id isolates the failing job, while tail_lines/max_bytes keep the response small. It does not, however, clarify precedence between job_id and run_id or how provider inference interacts with those ids, which the schema leaves implicit.

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?

Opens with a specific verb+resource ("Read CI logs") and immediately scopes it: whole run versus single job/step, with provider-specific limits. It also states the key differentiator ("Returns the tail, not the whole log") and names the sibling it is not, so an agent can separate it from project_ci_status without reading either schema.

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?

Contains explicit "Use when" and "Avoid when" clauses, with the alternative tool named (project_ci_status) and the condition that selects it (you only need pass/fail). It also gives the positive trigger (a run failed and you need the error) and the parameter recipe (pass job_id to isolate the failing job).

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