SkillTide

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

With no annotations provided, the description carries the full burden and does real work: it declares 'Read-only' and enumerates the returned record fields (name, url, description, tags, source, first/last seen). It omits what happens when the key does not resolve, which is the one behavioral detail a get-by-key tool would benefit from.

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 tight sentences, front-loaded with the action and key semantics, followed by return contents and safety. Every clause earns its place with no filler or repetition of the tool name.

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, so the description correctly compensates by listing the returned fields, and with no annotations it supplies the read-only nature itself. For a single-parameter lookup this is nearly complete; only not-found/error behavior is unaddressed.

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% so the baseline is 3, but the description adds genuine meaning beyond the schema's terse 'The entry key/slug' by pinpointing the key as 'the slug used in its SkillTide URL'. That origin detail helps the agent source the value correctly rather than guess at an ID format.

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') plus the exact addressing mechanism ('by its key (the slug used in its SkillTide URL)'). This cleanly separates it from the siblings: list_categories enumerates categories and search_tools queries for entries, while this fetches a single already-identified record.

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 implied rather than stated: the required key suggests 'use when you already have the slug,' which in turn implies search_tools is the path when you don't. But the description never says when to prefer this over its siblings or what to do if the key is unknown, so nothing is explicit.

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, the description carries the full burden, and it does disclose the key trait: "Read-only." It also describes the shape of what comes back (categories with counts, plus field tags). No permissions, caching, or size characteristics are mentioned, but for a zero-parameter read it is largely sufficient.

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 short sentences, front-loaded with the resource, then the return content, then the downstream use and the read-only trait. Nothing is padded.

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 parameterless read tool with no annotations and no output schema, the description covers purpose, return content, and the follow-up call pattern. A hint at the size or ordering of the returned categories would close the remaining gap.

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 tool takes no parameters, so the schema has nothing to document and the baseline of 4 applies. The description doesn't need to add parameter meaning and appropriately doesn't try.

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 gives a specific verb+resource ("List the catalogue's taxonomies") and enumerates the two taxonomy kinds with an example tag value, so the intent is unmistakable. It doesn't explicitly draw the line against get_tool, but the resource is distinct enough that confusion is unlikely.

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" states a concrete downstream use, effectively prescribing when to reach for this tool over search_tools. No exclusion conditions or prerequisites are given, so it falls short of a full when/when-not treatment.

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, the description carries the full disclosure burden and does name the key trait: 'Read-only' (non-mutating). It also compensates for the missing output schema by enumerating the return shape (name, url, one-line summary, tags). It does not mention ranking/relevance behavior, rate limits, or auth needs, so it stops short of a 5.

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 short sentences, front-loaded with what is searched, then what is returned, then the safety trait. No filler and nothing buried.

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 three-parameter search tool with no output schema, the description covers corpus scope, return fields and read-only behavior, which is most of what an agent needs. Minor gaps remain around result ordering/pagination semantics beyond the schema's limit cap.

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%, so query, limit and category are already fully documented in the schema, including a max-50 cap and example values. The description adds no syntax or semantic detail beyond the schema, so the 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 a sharply bounded resource: SkillTide's catalogue of 7,500+ MCP servers, agent skills and open-source projects plus 1,500 AI tools. The scope is concrete enough that an agent can distinguish it from get_tool, but the description never explicitly contrasts itself with its siblings, which is what a 5 would require.

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 implied by the verb 'search' — an agent will infer it should call this to discover entries — but there is no explicit statement of when to use this versus get_tool or list_categories, and no exclusions or prerequisites are given.

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