progrss

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

The readOnlyHint=true and openWorldHint=false annotations already establish that this is a safe, closed-domain read. The description adds value by disclosing the exact payload contents the agent will receive, including credit line and data year, but says nothing about what happens for a missing or invalid plate number.

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?

It is a single front-loaded sentence that opens with the scope ('One plate in full') and then lists the returned fields. The enumerated field list is long but each item is meaningful; the only cost is that it reads as a run-on list rather than structured lines.

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 simple one-parameter read tool with annotations covering the safety profile and a schema documenting the ID, the description is nearly complete: it fully answers what the agent gets back despite no output schema existing. Only error/missing-plate behavior and routing against siblings remain unstated.

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%, with the single 'id' parameter documented as a plate number such as "037", so the schema already carries the parameter semantics. The description adds no format, normalization, or lookup behavior beyond what the schema states, which is the expected baseline for a one-parameter tool.

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 names a specific verb and resource: retrieve one plate 'in full', and enumerates the fields returned (title, subtitle, takeaways, data table, source, claim types, links, credit line). It is clearly distinguishable from siblings like latest_plates or search_plates, which are plural/query tools, although the description never explicitly contrasts them.

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 description says it returns 'one plate in full', which suggests use when complete detail for a known plate is needed, but there is no explicit when-to-use statement, no exclusion, and no reference to the alternative siblings (search_plates, latest_plates, get_story) for lookup or listing.

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=true and openWorldHint=false, so safety is covered. The description adds one genuine behavioral fact beyond that: the response embeds the nested plates in reading order. It says nothing about missing-slug behavior or lookup failures, which is the main remaining gap.

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?

One short sentence with no filler, and the key detail (plates in reading order) is placed where it is read. It is near the edge of being too terse for a tool definition, but no words are wasted.

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 annotations covering safety and no output schema, the description is serviceable: the agent knows it fetches one story with ordered plates. It is still thin on error behavior and on how the returned story is shaped beyond the plates.

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 single parameter's description already explains the slug and its source, so the schema does the heavy lifting. The description only implies lookup-by-slug through 'one story' and adds no format or sourcing detail beyond the schema, making the 3 baseline appropriate.

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 sentence names a single specific resource ('one story') and what it comes with ('its plates in reading order'), which cleanly separates it from list_stories (many) and get_plate (a single plate). The retrieval verb is only implied by the tool name rather than stated, so it is clear but not fully self-contained.

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?

There is no when-to-use guidance, no exclusions, and no named alternative in the description. The only routing hint ('Story slug from list_stories') lives in the schema, not the description, so the agent gets no explicit signal about choosing this over list_stories or get_plate.

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=true and openWorldHint=false, so safety is covered. The description adds the one genuinely useful behavioral fact beyond them — results are ordered newest first — but says nothing about default result count, the maximum, or what a returned plate contains.

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?

It is a single short sentence with no padding, which is good, but the brevity comes at the cost of clarity — the garbled 'progrss' forces the reader to guess and there is no structure beyond one clause.

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, no parameter documentation, and an undefined domain term leave an agent unable to predict return shape or size. For a listing tool with a capped limit, the description should at least say how many items come back by default.

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% for the single 'limit' parameter (default 5, max 25), and the description never mentions limiting or result count at all. The constrained max of 25 is a meaningful behavior an agent would want to know before requesting more.

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?

It names a resource ('plates') and a scope (newest ones, newest-first ordering), so the general intent is inferable. But 'progrss' is a typo/garbled term, the domain meaning of 'plate' is never established, and nothing distinguishes this from sibling search_plates or get_plate.

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?

There is no when-to-use guidance and no mention of the obvious alternative, search_plates, which also returns plates. An agent must guess whether this is the browsing path and search_plates is the filtering path, or whether they overlap.

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=true and openWorldHint=false, so safety is covered. The description adds one genuine behavioral fact — stories are ordered as plate reading order — but says nothing about volume, pagination, or whether all stories are returned at once. Given no output schema exists, that leaves the response behavior largely undisclosed.

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?

It is a single short sentence with no filler, and the examples are efficient. But it is not front-loaded with an action verb, and the misspelled opening word plus the fragmentary "stories: storylines" construction cost clarity that a one-line description cannot afford.

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 zero-parameter, zero-output-schema listing tool, the description never says what comes back — a set of titles? slugs? full objects? whether the list is stable or paginated. The reading-order note is the only operational signal, which is thin for a tool whose entire contract is its return value.

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 zero parameters, which sets the baseline at 4, but the description adds no parameter-adjacent meaning either (e.g., no note that the unfiltered result set is small or complete). With nothing to document, 3 reflects that the schema does all the work and the description contributes nothing here.

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 identifies the resource as "storylines of plates in reading order" and gives concrete examples, which clarifies what a "story" is. However, it reads as a noun definition rather than a verb+resource statement — the "list" action exists only in the name/title — and the leading token "progrss" (presumably a typo for "progress") adds noise. It is distinguishable from get_story but the action is only implied.

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?

No when-to-use guidance is given, and none of the siblings (get_story, get_plate, search_plates, latest_plates) are mentioned, even though get_story is the obvious disambiguation point for a listing tool. An agent must infer from the names alone that this is the enumeration counterpart to get_story.

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 only declare read-only and non-open-world, leaving the description to say what comes back; it does, naming titles, URLs, sources and data years. That return detail matters because there is no output schema. It stops short of describing ranking behavior or how limit affects results.

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 the core action, then examples, then a routing sentence to get_plate — every part is functional. The parenthetical territory list partly duplicates the enum in the schema, which is minor redundancy rather than waste.

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 simple three-parameter read tool with no output schema, the description covers what is searched, how to phrase queries, and what is returned. Missing only secondary details like result ordering or behavior when a query matches nothing.

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 schema documents query and territory (67% coverage), and the description adds genuine meaning by showing example query phrasing and theme categories. The limit parameter is undocumented in both places, though its default and bounds make it largely self-explanatory.

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 ("Find progrss plates") and immediately defines what a plate is, plus concrete example queries. It also names the sibling get_plate and how it differs, so an agent can separate the two 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 clear use context via example keyword queries ("cobalt Congo", "India rice exports") and explicitly routes numeric lookups to get_plate. It does not address when to prefer latest_plates or list_stories over keyword search, leaving one sibling comparison to inference.

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