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

Beyond annotations, the description discloses strict unknown-key rejection ('A key this list does not name is rejected rather than dropped') and response-checking behavior ('The reply says how many conditions were stored, so check it matches what you sent'). These add real behavioral expectations not present in the annotation booleans.

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?

Purpose, usage, structure, strictness, and verification are all covered in a compact sequence, with the main instruction front-loaded. The fragment 'The saved view state.' is awkward, and some filter details duplicate the schema, but the complexity of the nested object justifies the length.

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?

Given the nested filter object, lack of output schema, and mutation semantics, the description provides enough structure and caveats to call the tool successfully. It lists allowed keys, warns against unknown keys, and advises verifying the reply count. It does not provide a full example, but the list_views copy workflow compensates.

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?

The schema already documents filter structure, and the description reinforces it while adding the practical instruction to copy an existing working filter. This helps an agent construct a valid filter. It adds less guidance for name, layout, groupBy, and shared, but the 60% schema coverage plus the copy-from-list_views workflow mitigates that gap.

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 opens with 'Save a filtered issue view,' a specific verb and resource that clearly identifies the creation action. It is distinguishable from siblings like update_view and delete_view, and the title reinforces the purpose.

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 description gives explicit instructional context: 'Call list_views first and copy the filter of a view that already works.' This is clear practical guidance, though it does not explicitly contrast with update_view for modifying existing views.

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