gateway_process_rebuild_backlog

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

The readOnlyHint: true annotation already covers the read-only safety profile. The description adds that the resulting backlog is 'staff-reviewed', which suggests it is meant for human evaluation, but it does not explain whether the backlog is persisted, how results are limited, or what side effects, if any, occur. The word 'Build' could even suggest mutation, though the annotation resolves that.

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 sentence with no filler. It front-loads the primary action and object, then specifies the data sources. Every word contributes meaning.

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?

With 7 parameters, 0% schema coverage, and an output schema, the one-sentence description is too thin to support correct invocation. An agent would not know what values to put in systems_json, candidates_json, comparisons_json, or project_ids_json, nor how period_days and limit affect the backlog. The presence of an output schema helps with return values, but the input contract remains largely unexplained.

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%, so the description must compensate. It names two conceptual inputs, 'process candidates' and 'Yonote comparison', which map to candidates_json and comparisons_json, but it does not clarify the other five parameters: limit, query, period_days, systems_json, and project_ids_json. The names of some parameters are self-explanatory, but the JSON-string formats and expected contents remain undefined.

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 ('Build'), a specific resource ('staff-reviewed Process Rebuild Backlog'), and its inputs ('process candidates and Yonote comparison'). This differentiates it from siblings like gateway_process_candidates_discover and gateway_process_compare_with_yonote, which produce those inputs rather than combining them. However, 'Build' is somewhat ambiguous about whether this is a read-only computation or a persistent write, which keeps it from a 5.

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 wording implies this tool consumes outputs from earlier process-discovery and comparison steps, since candidates_json and comparisons_json are inputs. But it never explicitly says 'run after gateway_process_candidates_discover and gateway_process_compare_with_yonote' or gives conditions for when not to use it. Usage context is implied rather than stated.

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