Griddo Docs

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful value beyond that by disclosing what is returned ('the full Markdown') and that the path must originate from the sibling tools, which is non-obvious workflow context.

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 sentences, both front-loaded with the operation and then the usage condition. No redundant restatement of the tool name or schema details.

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 single-parameter read tool with annotations covering safety and no output schema, the definition gives enough to call it correctly: what is fetched, the key, and when to prefer it. Return structure beyond 'full Markdown' is not elaborated, but that is not required here.

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 path parameter already documents accepted formats ('.md' suffix, leading slash, full URL), so the description need not compensate. It only restates 'by its path' without adding syntax meaning, 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+resource ('Fetch the full Markdown of one Griddo backoffice documentation page') with an explicit retrieval key ('by its path'). It also distinguishes itself from siblings search_griddo_editor_docs and list_griddo_editor_docs by naming them as the sources of the path.

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 a clear selection condition: 'Use it when the search excerpt is not enough to answer accurately,' which implicitly routes discovery to the sibling search/list tools. It names the alternatives but does not state an explicit when-not (e.g. don't use this for browsing or listing pages).

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is low. The description adds value by disclosing the result shape (grouped by section with title and URL) and the completeness guarantee ('every page'), which matters since no output schema exists.

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 returns first, then when to use it. No filler, no repetition, and the purpose is front-loaded ahead of the usage guidance.

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 trivial read-only listing tool with rich annotations, the description is nearly complete, describing both output shape and usage context. The one gap is the unaddressed lang parameter, which leaves a small hole in an otherwise adequate definition.

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 lang parameter has 0% schema description coverage, and the description never mentions it or the default 'es' value. An agent gets no explanation that this chooses the documentation language or that 'all' returns every language, so the description fails to compensate for the coverage gap.

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 (every page of the Griddo backoffice documentation), and even specifies the shape of the output: grouped by section, with title and URL. The 'before searching' phrasing implicitly distinguishes it from the search sibling, so an agent can tell list/retrieve-all apart from find-specific without opening schemas.

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 two concrete use scenarios ('get oriented before searching' and 'when the user asks what the documentation covers'), which cleanly routes the agent away from search_griddo_editor_docs for orientation tasks. It does not state an explicit when-not or name get_griddo_editor_doc as the single-page alternative, keeping it short of a 5.

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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and a closed (non-open-world) corpus, so the safety profile is covered. The description adds value beyond them by disclosing the return shape ('ranked excerpts with the canonical URL of each page') and the mandatory citation behavior. It does not mention ranking basis or pagination/limit interaction, which keeps it 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?

Content is front-loaded: scope first, then the usage imperative, then the exclusion. Both the usage and exclusion sentences are dense but each earns its place by preventing a real misrouting. Slightly long as a single block, but there is 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?

There is no output schema, yet the description explains what comes back (ranked excerpts plus canonical URLs) and what the agent should do with it (cite the URLs), which is exactly the missing piece. Combined with the explicit boundary against the DX server, an agent has everything needed to select and invoke this tool correctly.

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 67%, and the two documented parameters (lang, query) already carry their meaning in the schema, including the Spanish-primary nuance. The description adds nothing about parameter syntax or the limit ceiling beyond what the schema states, so it sits at the baseline for a partially documented schema.

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 ('Search the official Griddo documentation') and immediately scopes it to content authors and site administrators, enumerating the covered domains (backoffice, Author Experience, pages, modules, templates, forms, media gallery, roles, publishing). It also explicitly demarcates the sibling DX Docs MCP server, so an agent can distinguish this from related tools 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?

Gives explicit when-to-use ('before answering any question about how to do something in the Griddo backoffice'), a required follow-up action ('cite the URLs you get back'), and an explicit when-not-to-use with the alternative named ('Do NOT use it for developer questions about @griddo/core hooks... covered by the separate Griddo DX Docs MCP server'). Nothing is left to inference.

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