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

Annotations already mark it as read-only, and the description adds valuable behavioral detail beyond that: only 'visible' tasks are searchable, matching can occur on an 8-character id prefix with or without '#', and each row includes agency and project identifiers. This informs the agent about scoping and matching behavior beyond the structured annotations.

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 dense, front-loaded sentences cover the search fields, reference formats, and output row composition without wasted words. Each sentence adds distinct useful information, and the most important matching behavior comes first.

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 search tool, the description covers what is searched, how references work, and what each row carries, which is enough for most correct invocations. It does not mention result ordering, pagination, or default limit behavior, and client_id/agency_id remain unexplained, but the core usage is well covered given the annotations.

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 only 33%, so the description carries a heavier burden. It meaningfully explains the query parameter (matches title, description, goal, references) and project_id filtering, but it does not clarify limit, client_id, agency_id, or parent_id semantics. Several parameters remain effectively undocumented apart from the schema's brief parent_id/project_id notes.

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 uses a specific verb and resource: full-text search over tasks by title, description, and goal, and also matches task reference prefixes or full UUIDs. This clearly distinguishes it from sibling get/list tools and gives an agent immediate understanding of what the tool does.

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 clear usage context: it searches visible tasks by text or task reference, and advises filtering by project_id to scope results to a single project. It does not explicitly name alternatives or when-not-to-use cases, but the search-vs-list/get distinction is implied strongly by the wording.

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