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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description adds real behavioural context beyond them, notably the data-coverage caveat that sector matching answers NOT_COVERED while websites are unread and that firms stay reachable via portfolio-company investors. It also discloses the return identity format (dfx:vc: ids). It does not mention pagination or sort semantics.

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-loaded with what a card contains before moving to filters, and it ends with the key output contract and exclusion note. It is dense but mostly earns its words; the nested parenthetical listing is slightly hard to parse but not wasteful.

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 no output schema, the description usefully sketches the return shape (compact cards, dfx:vc: ids) and the exclusion set. But for a 12-parameter tool with 0 required params it omits default/max behaviours (limit 25/50), sort modes, and several filters, so an agent still has to open the schema for several decisions.

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 only 33% across 12 parameters, so the description must carry weight; it does explain five filter axes (sector, stage, state, active/raising, emerging manager) and matches 'active or raising' to the boolean params. However, it says nothing about city, sort, limit (max 50), query, min_investments or recent_activity_days, leaving half the surface undocumented.

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 and resource ('Venture firms as compact cards') and enumerates the card contents (stated sectors/stages/geography/check size plus observed behaviour, funds, people counts). It explicitly draws the boundary against siblings: 'Funds, people and individual deals are not on these cards,' separating it from search_vc_funds and search_vc_investments.

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?

It gives clear filtering context ('Filter by sector, stage, state, active or raising, emerging manager'), so the agent knows the axes for narrowing results. It also implicitly routes the agent elsewhere for funds/people/deals, but never states when to prefer get_vc_firm (single-firm lookup) over this search, so the routing is not fully explicit.

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