conduyt_search

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

With no annotations, the description carries the burden well: it discloses per-leg 3-second budgets, that a cut leg is omitted and reported via `partial: true` / `partialLegs`, and that short terms cause `skippedLegs`. It stops short of covering permissions, result ranking/ordering, or how results are aggregated across legs.

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-loads the scope in the first clause, then layers in match-length rules and partial-result behavior. Dense with semicolons and backticked flags, but every clause conveys operative information; only light trimming would be possible.

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?

No output schema exists, and the description compensates by explaining the `partial`/`partialLegs`/`skippedLegs` response fields and `textMinLength`. It is nearly complete for a search tool, though it doesn't describe the general result shape or ordering, which an agent might need to interpret results.

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% and the schema already documents query, limit, and cursor semantics. The description restates the query matching rules (2+ chars for names/emails/phones/deal titles, 3+ for free text) with only slightly more detail than the schema, and says nothing about limit defaults or cursor pagination beyond what the schema provides. Baseline 3 applies.

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?

States a specific verb ('search') and an explicit global scope, then enumerates the entity families covered (contacts, deals, companies, tasks, notes, messages, activities, document text). This clearly distinguishes it from the entity-scoped list_* siblings such as conduyt_list_contacts and conduyt_list_deals.

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?

Gives actionable guidance on the minimum term length per leg and tells the agent to 'retry with a longer or more specific term' when text legs are skipped. It does not, however, explicitly contrast with the per-entity list/get siblings or state when a scoped search would be preferable.

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