accelo_list_activities

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that the upstream GET /activities ignores _search, that this tool rejects `search` up front with a structured error rather than silently returning unrelated data, and it details the against_type resolution chain. It omits auth/permission needs, rate-limit behavior, and return/pagination semantics beyond the page/limit args.

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?

Well front-loaded — scope, the critical search limitation, then the resolution workflow and args. It is long but mostly justified; however the 'search is not supported / no subject filter' warning is repeated three times (body, the anti-pattern block, and the args section), which is redundant. The self-referential 'See the tool description' line inside the description is also noise.

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 no annotations, no output schema, and a free-form filters object, the description supplies nearly everything needed to call the tool correctly: scope, against-resolution logic, an explicit anti-pattern with workarounds, and parameter details. Minor gap is the shape of the returned activity set and default ordering, which an agent must infer.

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, and it does: it enumerates the allowed filter keys, documents fields syntax with an example ('against()'), explains page is 0-indexed and limit maxes at 100, and flags the absence of a `subject` filter. It covers all five parameters with meaning the bare schema lacks.

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 ('List activities') and enumerates the concrete subtypes (notes, emails, calls, meetings), then explains what an activity is and how it attaches 'against' an object. An agent can distinguish it from siblings such as accelo_list_thread_activities, accelo_get_activity, and accelo_count_activities without opening any 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?

Provides explicit when-to-use and when-NOT-to-use guidance: it states plainly that subject/text search is unsupported and then names the alternatives (accelo_list_thread_activities, scoped accelo_list_activities with filters, accelo_run_filter) with the condition that selects each. This is a textbook routing instruction.

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