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

With no annotations, the description carries the full burden; it does disclose the read-only nature and the full field set returned, which is genuine behavioral value. It omits what happens when the key is unknown (error vs. empty result) and any auth or rate considerations, leaving a meaningful gap for a lookup tool.

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?

Two short sentences, zero filler, with the identifying scope and return contents front-loaded before the read-only note. Every clause earns its place.

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 one-parameter read tool with no output schema, listing the returned fields plus the read-only guarantee covers nearly everything an agent needs. The only gap is failure behavior for a missing key.

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 single parameter is fully documented in the schema (100% coverage), and the description adds real meaning beyond it by explaining that the key is the slug appearing in the entry's Anclum URL. That is more than the schema's bare 'entry key/slug'.

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 ('Get one catalogue entry by its key') and immediately enumerates the record contents, which cleanly separates it from search_tools (query-based) and list_categories (category enumeration). An agent knows exactly what this returns without opening a 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?

Usage is only implied: the requirement of an exact key suggests it is the follow-up to a search, but the description never names search_tools as the way to obtain a key or states when not to use it. The 'slug used in its Anclum URL' hint helps the agent source the key but is not an explicit when-to-use rule.

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

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

No annotations are provided, so the description must carry the behavioral load. It declares 'Read-only' and discloses that counts are included, which is valuable. However, it says nothing about response size, ordering, caching, or whether the taxonomy list is complete — modest gaps for an unannotated tool.

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?

Two compact sentences, front-loaded with what is listed, followed by the follow-up action. Nothing restates the name or wastes tokens.

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 must convey return content, and it does: categories with counts plus field tags with examples. It stops short of describing the response shape (flat list vs object with two keys), which is the only real gap for such a simple tool.

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?

There are zero parameters, which is the baseline-4 case. The description reinforces that no filtering input is needed by framing the call as a full taxonomy listing.

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 ('List') and resource ('the catalogue's taxonomies'), then enumerates exactly what comes back: AI-tool categories with counts and field tags with example values. This distinguishes it clearly from get_tool (single fetch) and search_tools (query-driven search).

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?

'Useful for then calling search_tools with a category' gives an explicit downstream use and names the sibling it feeds. It lacks an explicit 'do not use this if...' exclusion, but the usage context is unambiguous for a zero-param discovery tool.

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

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

With no annotations present, the description does carry the safety signal itself by declaring 'Read-only', and it states the return fields and corpus scope, which is genuinely useful. It is silent on pagination/limit behaviour, whether a total match count is returned, and any rate limits, which is a real gap for an unannotated tool an agent may call repeatedly.

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?

Two tight sentences: what it searches, what comes back, and the read-only guarantee. Scope and result shape are front-loaded with no filler.

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, but the description enumerates the returned fields, which covers the main return-value question, and the corpus size sets expectations about coverage. It lacks any note about result ordering or how to retrieve fuller detail after finding a candidate, which would fully close the loop with the get_tool sibling.

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 100%, and each parameter (query, category, limit) is documented in the schema with defaults and examples, so the description does not need to compensate. The description adds no parameter-level meaning beyond what the schema already gives, so the baseline of 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 resource (Anclum's catalogue of MCP servers, agent skills, AI projects and tools) with the corpus size, so the agent knows exactly what is being searched. It does not name the siblings get_tool or list_categories, so the boundary between searching and fetching a detail record is only implied by the listed return fields.

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 verb 'Search' plus the returned fields (name, url, one-line summary, tags) implies this is the discovery entry point that precedes get_tool, but no explicit when-to-use or when-not statement is given. Nothing routes the agent to list_categories for browsing or warns that this is for keyword lookup rather than full detail retrieval.

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